run_results.zip
run_results
Crystal
LAPO_median
e_1_r_0.65
live_run
1
0
results_gemini-2.5-pro_simple_T_20251130_181553.json
43.3 kB
Preview
Download
results_gemini-2.5-pro_simple_T_20251230_202829.json
43.3 kB
Preview
Download
results_gemini-2.5-pro_simple_T_20251231_172843.json
43.0 kB
Preview
Download
results_gemini-2.5-pro_simple_T_20260102_194105.json
43.0 kB
Preview
Download
results_gemini-2.5-pro_simple_T_20260103_193522.json
42.9 kB
Preview
Download
results_gemini-2.5-pro_simple_T_20260109_205452.json
43.1 kB
Preview
Download
HH02
results_gemini-2.5-pro_simple_T_20251224_000216.json
43.3 kB
Preview
Download
results_gemini-2.5-pro_simple_T_20251226_133712.json
43.5 kB
Preview
Download
results_gemini-2.5-pro_simple_T_20251227_002109.json
43.5 kB
Preview
Download
results_gemini-2.5-pro_simple_T_20251227_111807.json
43.4 kB
Preview
Download
results_gemini-2.5-pro_simple_T_20251229_195022.json
43.6 kB
Preview
Download
results_gemini-2.5-pro_simple_T_20260110_133413.json
43.6 kB
Preview
Download
4
0
results_gemini-2.5-pro_simple_T_20251208_231620.json
43.5 kB
Preview
Download
results_gemini-2.5-pro_simple_T_20251224_000021.json
43.8 kB
Preview
Download
results_gemini-2.5-pro_simple_T_20251231_173006.json
43.6 kB
Preview
Download
results_gemini-2.5-pro_simple_T_20260103_002121.json
43.5 kB
Preview
Download
results_gemini-2.5-pro_simple_T_20260106_123458.json
43.6 kB
Preview
Download
results_gemini-2.5-pro_simple_T_20260106_164326.json
43.5 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_114327.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_115324.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_115623.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_115922.json
22.6 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_120249.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_120618.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_121011.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_121621.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_121947.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_122501.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_122831.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_123312.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_123547.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_123829.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_124103.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_124433.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_124739.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_125019.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_125408.json
22.5 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_125649.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_125924.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_130215.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_130451.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_130955.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_132338.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_133226.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_133633.json
22.4 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_134015.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_134908.json
23.2 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_135501.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_140422.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_143838.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_004454.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_005251.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_005531.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_010853.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_011123.json
22.6 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_011420.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_012628.json
23.2 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_015203.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_081250.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_081526.json
23.7 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_081850.json
23.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_082145.json
23.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_082435.json
23.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_082709.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_082952.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_083233.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_083517.json
22.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_083803.json
22.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_084051.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_084337.json
23.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_084644.json
23.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_084921.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_085211.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_085447.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_085704.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_085922.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_090243.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_090517.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_090801.json
23.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_091023.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_091310.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_091558.json
22.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_091851.json
23.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_092214.json
23.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_092448.json
23.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_092738.json
22.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_093030.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_093327.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_093615.json
23.5 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_093906.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_094215.json
23.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_094545.json
23.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_094817.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_095155.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_095436.json
23.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_095717.json
23.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_095944.json
23.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_100300.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_214555.json
23.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_214802.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_214944.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_215155.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_215400.json
23.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_215608.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_215806.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_220019.json
23.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_220208.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_220430.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_220643.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_220852.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_221056.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_221305.json
23.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_221456.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_221638.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_221846.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_222055.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_222315.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_222534.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_222745.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_222952.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_223216.json
23.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_223424.json
24.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_223614.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_223813.json
23.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_224018.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_224238.json
24.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_224428.json
22.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_224612.json
23.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_224817.json
23.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_225023.json
22.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_225301.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_225441.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_225655.json
22.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_225853.json
23.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_230102.json
24.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_230321.json
23.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_230523.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_230726.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_162004.json
23.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_162237.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_162403.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_162722.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_163017.json
23.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_163305.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_163551.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_163842.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_164140.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_164455.json
23.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_164633.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_164938.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_165232.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_165555.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_165836.json
23.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_170156.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_170449.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_170800.json
23.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_171041.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_171359.json
23.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_171605.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_171853.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_172135.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_172423.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_172746.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_173019.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_173338.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_173649.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_173834.json
23.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_174116.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_174354.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_174714.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_175010.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_175238.json
23.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_175529.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_175755.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_180115.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_180353.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_180654.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_180943.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_083832.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_083934.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084032.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084140.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084240.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084345.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084445.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084544.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084645.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084748.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084849.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084949.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085054.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085154.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085257.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085357.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085457.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085558.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085659.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085759.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085859.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090001.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090101.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090201.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090301.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090401.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090500.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090602.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090701.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090801.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090902.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091002.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091102.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091203.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091304.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091408.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091506.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091605.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091705.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091804.json
23.1 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251107_180020.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251107_182416.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251107_182845.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251107_183334.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251107_192259.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251119_171205.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251119_171803.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251119_172311.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251107_154732.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251107_160020.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251107_161624.json
23.0 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251107_164709.json
23.8 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251119_171411.json
23.8 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251119_172115.json
23.8 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251119_172958.json
23.8 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251119_173750.json
23.2 kB
Preview
Download
results_gpt-5_median_T_20251017_154433.json
30.6 kB
Preview
Download
results_gpt-5_median_T_20251017_162559.json
30.3 kB
Preview
Download
results_gpt-5_median_T_20251018_140837.json
31.3 kB
Preview
Download
results_gpt-5_median_T_20251120_081008.json
22.6 kB
Preview
Download
results_gpt-5_median_T_20251120_084522.json
22.6 kB
Preview
Download
results_gpt-5_median_T_20251120_092612.json
23.2 kB
Preview
Download
results_gpt-5_median_T_20251123_211219.json
22.5 kB
Preview
Download
results_gpt-5_median_T_20260123_163410.json
22.6 kB
Preview
Download
e_1_r_0.96
results_-work-models-google-gemma-3-12b-it_median_T_20251207_114948.json
23.2 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_115239.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_115601.json
22.5 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_115846.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_120321.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_120546.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_120826.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_121046.json
22.4 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_121328.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_122305.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_122540.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_122853.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_123410.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_123654.json
22.6 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_123944.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_124303.json
23.2 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_124710.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_125030.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_125345.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_130020.json
22.6 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_130827.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_132128.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_132349.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_132629.json
22.6 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_132947.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_134249.json
22.6 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_135113.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_135719.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_140210.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_141748.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_143436.json
23.4 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251207_144408.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_001511.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_010720.json
22.5 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_011006.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_011751.json
23.2 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_012251.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_012534.json
23.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_014309.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20251209_015042.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_081250.json
23.5 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_081520.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_081738.json
23.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_082008.json
23.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_082326.json
23.5 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_082554.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_082928.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_083203.json
22.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_083437.json
23.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_083658.json
22.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_083930.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_084238.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_084549.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_084909.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_085235.json
23.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_085505.json
23.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_085733.json
23.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_090028.json
22.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_090257.json
22.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_090531.json
22.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_090757.json
22.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_091016.json
22.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_091249.json
23.5 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_091521.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_091754.json
23.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_092017.json
23.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_092335.json
23.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_092619.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_092958.json
23.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_093220.json
23.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_093520.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_093850.json
23.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_094233.json
22.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_094457.json
23.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_094753.json
23.5 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_095023.json
22.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_095249.json
23.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_095522.json
23.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_095745.json
22.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20251208_100011.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_214555.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_214751.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_214944.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_215155.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_215414.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_215632.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_215850.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_220042.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_220232.json
22.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_220430.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_220643.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_220839.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_221040.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_221252.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_221508.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_221711.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_221948.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_222145.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_222335.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_222526.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_222745.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_223019.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_223256.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_223513.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_223732.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_223934.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_224141.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_224404.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_224603.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_224823.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_225036.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_225246.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_225435.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_225632.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_225832.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_230020.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_230215.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_230432.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_230634.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20251207_230853.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_162012.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_162231.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_162514.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_162715.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_162930.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_163208.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_163440.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_163719.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_163946.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_164249.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_164522.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_164743.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_165004.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_165243.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_165531.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_165759.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_170030.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_170257.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_170526.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_170809.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_171054.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_171328.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_171600.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_171825.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_172104.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_172340.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_172558.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_172854.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_173127.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_173405.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_173644.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_173856.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_174103.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_174325.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_174543.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_174831.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_175116.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_175345.json
23.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_175617.json
23.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20251207_175843.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_083832.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_083934.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084035.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084140.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084240.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084340.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084445.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084545.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084645.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084748.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084848.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_084949.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085052.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085154.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085257.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085400.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085501.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085607.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085708.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085809.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_085911.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090018.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090120.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090221.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090321.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090422.json
23.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090523.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090626.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090726.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090828.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_090929.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091029.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091131.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091231.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091331.json
23.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091431.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091533.json
23.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091633.json
23.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091731.json
23.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20251207_091831.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251107_181759.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251107_184130.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251107_184409.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251107_184818.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251120_122226.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251120_122655.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251120_123138.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251120_123613.json
23.0 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251107_180602.json
23.0 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251107_182451.json
23.6 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251107_183659.json
23.0 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251107_192847.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251120_104128.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251120_104841.json
23.1 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251120_105638.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251120_110529.json
23.2 kB
Preview
Download
results_gpt-5_median_T_20251120_110726.json
22.6 kB
Preview
Download
results_gpt-5_median_T_20251120_114652.json
22.6 kB
Preview
Download
results_gpt-5_median_T_20251120_120949.json
22.6 kB
Preview
Download
results_gpt-5_median_T_20251120_124408.json
23.2 kB
Preview
Download
results_gpt-5_median_T_20251123_211501.json
23.3 kB
Preview
Download
results_gpt-5_median_T_20251123_214758.json
22.7 kB
Preview
Download
results_gpt-5_median_T_20251123_221814.json
22.5 kB
Preview
Download
results_gpt-5_median_T_20251123_224559.json
23.2 kB
Preview
Download
LAPO_median_anon
e_1_r_0.96
results_claude-sonnet-4-5_anon_T_20251126_123916.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_anon_T_20251126_124232.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_anon_T_20251126_124553.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_anon_T_20251126_132814.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_anon_T_20251126_133157.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_anon_T_20251126_142918.json
22.9 kB
Preview
Download
results_claude-sonnet-4-5_anon_T_20251126_143243.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_anon_T_20251126_144132.json
23.0 kB
Preview
Download
results_gemini-2.5-pro_anon_T_20251126_103140.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_anon_T_20251126_104028.json
23.0 kB
Preview
Download
results_gemini-2.5-pro_anon_T_20251126_105229.json
23.0 kB
Preview
Download
results_gemini-2.5-pro_anon_T_20251126_110142.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_anon_T_20251126_111115.json
23.0 kB
Preview
Download
results_gemini-2.5-pro_anon_T_20251126_111907.json
23.5 kB
Preview
Download
results_gemini-2.5-pro_anon_T_20251126_112718.json
22.8 kB
Preview
Download
results_gemini-2.5-pro_anon_T_20251126_160904.json
22.9 kB
Preview
Download
results_gpt-5_anon_T_20251124_174817.json
22.9 kB
Preview
Download
results_gpt-5_anon_T_20251124_190438.json
22.4 kB
Preview
Download
results_gpt-5_anon_T_20251124_195121.json
22.4 kB
Preview
Download
results_gpt-5_anon_T_20251124_202850.json
22.4 kB
Preview
Download
results_gpt-5_anon_T_20251124_210112.json
22.5 kB
Preview
Download
results_gpt-5_anon_T_20251124_214021.json
22.4 kB
Preview
Download
results_gpt-5_anon_T_20251126_144625.json
22.6 kB
Preview
Download
results_gpt-5_anon_T_20251126_151914.json
22.4 kB
Preview
Download
LAPO_minimal
e_1_r_0.65
results_claude-sonnet-4-5_minimal_T_20251108_134754.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_minimal_T_20251119_144737.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_minimal_T_20251122_194358.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_minimal_T_20251122_195921.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_minimal_T_20251123_141711.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_minimal_T_20251123_142000.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_minimal_T_20251123_142514.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_minimal_T_20251123_142732.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251107_194608.json
23.8 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251107_195353.json
22.9 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251107_200200.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251107_201010.json
23.0 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251107_202754.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251119_144045.json
23.8 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251119_144737.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251119_145622.json
23.2 kB
Preview
Download
results_gpt-5_minimal_T_20251017_124102.json
30.7 kB
Preview
Download
results_gpt-5_minimal_T_20251017_125420.json
31.5 kB
Preview
Download
results_gpt-5_minimal_T_20251107_232029.json
23.0 kB
Preview
Download
results_gpt-5_minimal_T_20251107_233727.json
23.0 kB
Preview
Download
results_gpt-5_minimal_T_20251119_135958.json
23.2 kB
Preview
Download
results_gpt-5_minimal_T_20251119_142031.json
22.6 kB
Preview
Download
results_gpt-5_minimal_T_20251123_120430.json
23.6 kB
Preview
Download
results_gpt-5_minimal_T_20251123_122407.json
23.6 kB
Preview
Download
e_1_r_0.96
results_claude-sonnet-4-5_minimal_T_20251108_073704.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_minimal_T_20251108_074736.json
23.2 kB
Preview
Download
results_claude-sonnet-4-5_minimal_T_20251122_230203.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_minimal_T_20251123_120639.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_minimal_T_20251123_123801.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_minimal_T_20251123_163059.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_minimal_T_20251123_163538.json
23.0 kB
Preview
Download
results_claude-sonnet-4-5_minimal_T_20251123_164022.json
23.0 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251108_083834.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251108_085444.json
23.8 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251122_225226.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251122_230034.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251122_230751.json
23.8 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251123_142317.json
23.2 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251123_143157.json
23.0 kB
Preview
Download
results_gemini-2.5-pro_minimal_T_20251123_144104.json
23.0 kB
Preview
Download
results_gpt-5_minimal_T_20251016_141138.json
31.7 kB
Preview
Download
results_gpt-5_minimal_T_20251016_143713.json
31.7 kB
Preview
Download
results_gpt-5_minimal_T_20251016_154658.json
30.9 kB
Preview
Download
results_gpt-5_minimal_T_20251123_142121.json
23.8 kB
Preview
Download
results_gpt-5_minimal_T_20251123_144306.json
23.8 kB
Preview
Download
results_gpt-5_minimal_T_20251123_150440.json
23.8 kB
Preview
Download
results_gpt-5_minimal_T_20251123_163152.json
23.6 kB
Preview
Download
results_gpt-5_minimal_T_20251123_165740.json
23.2 kB
Preview
Download
RPL
LAPO_median
e_1_r_0.655
results_-work-models-google-gemma-3-12b-it_median_T_20260129_152004.json
71.8 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260129_152714.json
72.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_110104.json
68.5 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_110610.json
68.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_111046.json
68.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_111623.json
69.2 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_112052.json
68.6 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_112607.json
68.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_113055.json
67.6 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_113631.json
68.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_114114.json
69.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_114444.json
67.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_114937.json
68.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_115420.json
67.5 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_115939.json
69.5 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_120336.json
68.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_120845.json
68.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_121400.json
68.5 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_121833.json
68.4 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_122345.json
68.7 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_122825.json
68.2 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_123418.json
68.2 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_123901.json
67.5 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_124243.json
73.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_124837.json
67.7 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_125314.json
67.8 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_125819.json
68.4 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_130332.json
68.4 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_130806.json
67.4 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_131222.json
67.8 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_131728.json
67.4 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_132145.json
67.9 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_132546.json
68.5 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_133101.json
68.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_133609.json
69.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_134115.json
67.7 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_134635.json
69.9 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_135302.json
68.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_135742.json
68.2 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_140254.json
67.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_152855.json
73.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_153516.json
72.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_154224.json
68.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_155134.json
67.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_155659.json
70.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_161453.json
68.7 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_162251.json
68.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_162748.json
69.7 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_163258.json
69.5 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_163850.json
79.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_165418.json
68.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_170237.json
67.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_170724.json
69.7 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_171558.json
68.5 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_172056.json
69.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_172815.json
69.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_173402.json
80.5 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_174921.json
57.5 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_180157.json
67.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_180744.json
67.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_181256.json
74.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_181900.json
68.5 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_182349.json
74.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_182953.json
69.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_183442.json
71.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_184241.json
68.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_184741.json
68.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_185225.json
63.5 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_190801.json
69.7 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_191323.json
73.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_192012.json
68.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_192756.json
68.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_193659.json
67.7 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_194245.json
69.1 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_194751.json
68.5 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_195400.json
68.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_200038.json
60.1 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_201424.json
70.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_143936.json
69.1 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_144454.json
68.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_153702.json
68.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_154122.json
68.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_154509.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_154847.json
69.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_155219.json
70.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_155611.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_155945.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_160342.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_160736.json
69.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_161102.json
69.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_161425.json
69.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_161827.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_162201.json
70.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_162633.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_163053.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_163513.json
69.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_163825.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_164250.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_164613.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_165014.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_165424.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_165818.json
69.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_170158.json
70.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_170524.json
69.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_170850.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_171243.json
69.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_171645.json
69.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_172017.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_172340.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_172707.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_173107.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_173534.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_174006.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_174340.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_174725.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_175044.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_175417.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_175827.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_180234.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_180620.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260203_204016.json
70.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_145750.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_150313.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_150734.json
69.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_151336.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_151737.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_152319.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_152856.json
70.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_153413.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_154008.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_154544.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_155118.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_155747.json
69.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_160418.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_161039.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_161630.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_162114.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_162723.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_163231.json
68.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_163856.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_164445.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_165023.json
69.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_165606.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_170156.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_170756.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_171310.json
68.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_171927.json
68.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_172448.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_173023.json
68.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_173647.json
69.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_174200.json
69.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_174716.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_175307.json
68.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_175934.json
68.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_180525.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_181117.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_181659.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_182243.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_182741.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_183351.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_153512.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_153710.json
56.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_154438.json
68.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_154643.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_154837.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_155035.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_155231.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_155425.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_155623.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_155819.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_160016.json
69.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_160214.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_160411.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_160609.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_160805.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_161000.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_161159.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_161353.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_161548.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_161748.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_161945.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_162139.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_162337.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_162535.json
69.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_162734.json
68.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_163010.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_163205.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_163403.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_163559.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_163755.json
68.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_163955.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_164149.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_164345.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_164539.json
66.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_165428.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_165629.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_165827.json
68.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_170015.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_170209.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_170418.json
69.8 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20260120_204733.json
78.7 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20260120_210256.json
45.9 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20260120_212727.json
79.5 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20260120_215444.json
78.7 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20260120_224001.json
76.8 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20260120_230316.json
78.5 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20260123_150752.json
78.9 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20260123_155043.json
78.9 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251121_103027.json
72.8 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251121_104916.json
72.6 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251121_110113.json
72.2 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251121_111324.json
73.0 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251121_112744.json
72.6 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251121_113714.json
73.1 kB
Preview
Download
results_gemini-2.5-pro_median_T_20260122_210858.json
80.6 kB
Preview
Download
results_gemini-2.5-pro_median_T_20260123_174714.json
79.3 kB
Preview
Download
results_gpt-5_median_T_20260120_231214.json
77.6 kB
Preview
Download
results_gpt-5_median_T_20260121_073127.json
76.2 kB
Preview
Download
results_gpt-5_median_T_20260121_100249.json
76.6 kB
Preview
Download
results_gpt-5_median_T_20260121_123159.json
76.6 kB
Preview
Download
results_gpt-5_median_T_20260122_152953.json
76.6 kB
Preview
Download
results_gpt-5_median_T_20260122_190218.json
78.0 kB
Preview
Download
results_gpt-5_median_T_20260123_115929.json
76.8 kB
Preview
Download
results_gpt-5_median_T_20260123_160223.json
78.2 kB
Preview
Download
e_1_r_0.93
results_-work-models-google-gemma-3-12b-it_median_T_20260129_152605.json
63.9 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260129_154718.json
57.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260129_164049.json
64.4 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260129_174725.json
74.6 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_110740.json
68.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_111247.json
67.4 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_111712.json
68.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_112229.json
67.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_112644.json
67.7 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_113102.json
67.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_113548.json
69.4 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_114013.json
67.8 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_114522.json
67.4 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_114942.json
68.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_115414.json
67.8 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_115842.json
67.7 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_120231.json
68.4 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_120706.json
68.2 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_121230.json
68.6 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_121622.json
69.2 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_122104.json
68.7 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_122538.json
69.1 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_123059.json
67.6 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_123532.json
68.5 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_124023.json
68.7 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_124612.json
67.4 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_125046.json
73.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_125533.json
67.9 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_130006.json
67.5 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_130440.json
67.7 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_130944.json
68.8 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_131529.json
69.0 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_132037.json
68.6 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_132554.json
67.8 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_132920.json
68.3 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_133238.json
68.9 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_133613.json
67.8 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_134057.json
68.8 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_134705.json
68.4 kB
Preview
Download
results_-work-models-google-gemma-3-12b-it_median_T_20260131_135124.json
69.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_153303.json
70.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_153933.json
68.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260129_154828.json
78.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_111817.json
68.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_112434.json
69.1 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_113007.json
68.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_113526.json
69.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_114137.json
68.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_114701.json
70.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_115310.json
68.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_115833.json
72.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_120418.json
68.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_120931.json
68.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_121837.json
70.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_122653.json
68.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_123231.json
68.5 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_123916.json
73.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_124616.json
68.7 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_125114.json
71.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_125832.json
68.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_130635.json
68.5 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_131158.json
69.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_131734.json
68.3 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_132433.json
67.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_133352.json
69.1 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_134117.json
67.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_134846.json
69.1 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_135657.json
72.4 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_140442.json
69.7 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_141032.json
68.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_141617.json
72.2 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_142243.json
68.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_143028.json
71.6 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_143820.json
68.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_144354.json
68.8 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_144914.json
68.0 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_145414.json
67.5 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_145930.json
67.9 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_150739.json
68.7 kB
Preview
Download
results_-work-models-google-gemma-3-27b-it_median_T_20260131_151321.json
68.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_154103.json
68.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_154506.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_154908.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_155340.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_155743.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_160208.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_160619.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_160940.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_161300.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_161651.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_162037.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_162509.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_162856.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_163346.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_163840.json
68.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_164214.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_164601.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_165022.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_165429.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_165842.json
69.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_170317.json
68.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_170710.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_171038.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_171421.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_171852.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_172251.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_172643.json
69.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_173102.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_173418.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_173751.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_174123.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_174600.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_174947.json
68.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_175319.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_175719.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_180141.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_180523.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_180957.json
75.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_182406.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct-AWQ_median_T_20260129_182749.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_080816.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_145859.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_150543.json
68.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_151043.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_151613.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_152224.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_152811.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_153249.json
69.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_153904.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_154440.json
69.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_155050.json
68.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_155648.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_160240.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_160717.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_161324.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_161928.json
69.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_162417.json
69.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_162931.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_163447.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_163936.json
67.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_164612.json
68.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_165214.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_165703.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_170156.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_170804.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_171258.json
69.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_171932.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_172507.json
69.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_173051.json
68.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_173701.json
70.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_174159.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_174801.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_175415.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_175932.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_180457.json
68.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_181103.json
68.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_181628.json
68.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_182233.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_182708.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-70B-Instruct_median_T_20260204_183230.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_153518.json
69.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_153726.json
68.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_153923.json
68.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_154121.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_154314.json
69.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_154515.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_154723.json
69.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_154921.json
68.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_155119.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_155313.json
68.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_155511.json
68.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_155711.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_155904.json
68.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_160102.json
68.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_160255.json
68.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_160451.json
68.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_160647.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_160841.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_161036.json
69.2 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_161228.json
68.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_161423.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_161649.json
68.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_161842.json
68.7 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_162038.json
68.4 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_162238.json
69.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_162426.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_162624.json
68.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_162814.json
69.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_163013.json
69.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_163220.json
69.0 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_163417.json
69.5 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_163602.json
69.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_163754.json
68.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_163957.json
68.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_164143.json
69.1 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_164330.json
68.8 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_164523.json
69.3 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_164712.json
68.6 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_164911.json
68.9 kB
Preview
Download
results_-work-models-meta-llama-Llama-3.1-8B-Instruct_median_T_20260129_165107.json
69.0 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251128_143559.json
72.3 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251128_144525.json
72.8 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251128_145419.json
70.9 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251128_150352.json
70.9 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251128_151221.json
71.1 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251205_151959.json
72.8 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251205_152939.json
72.6 kB
Preview
Download
results_claude-sonnet-4-5_median_T_20251205_153909.json
70.5 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251127_205130.json
72.6 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251127_212320.json
72.0 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251127_213223.json
71.4 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251129_184756.json
72.4 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251129_211705.json
71.5 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251204_014716.json
73.7 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251204_020013.json
72.4 kB
Preview
Download
results_gemini-2.5-pro_median_T_20251204_123501.json
72.8 kB
Preview
Download
results_gpt-5_median_T_20251128_144004.json
71.0 kB
Preview
Download
results_gpt-5_median_T_20251128_184253.json
70.7 kB
Preview
Download
results_gpt-5_median_T_20251128_215140.json
70.5 kB
Preview
Download
results_gpt-5_median_T_20251128_234121.json
69.3 kB
Preview
Download
results_gpt-5_median_T_20251129_120827.json
72.1 kB
Preview
Download
results_gpt-5_median_T_20251204_175448.json
69.6 kB
Preview
Download
results_gpt-5_median_T_20251205_123634.json
69.8 kB
Preview
Download
results_gpt-5_median_T_20251205_225843.json
70.5 kB
Preview
Download
LAPO_median_anon
e_1_r_0.93
results_claude-sonnet-4-5_anon_T_20251128_143517.json
56.0 kB
Preview
Download
results_claude-sonnet-4-5_anon_T_20251128_144300.json
56.1 kB
Preview
Download
results_claude-sonnet-4-5_anon_T_20251128_145002.json
55.7 kB
Preview
Download
results_claude-sonnet-4-5_anon_T_20251128_145740.json
55.6 kB
Preview
Download
results_claude-sonnet-4-5_anon_T_20251128_150428.json
55.4 kB
Preview
Download
results_claude-sonnet-4-5_anon_T_20251204_131217.json
55.8 kB
Preview
Download
results_claude-sonnet-4-5_anon_T_20251204_134051.json
55.9 kB
Preview
Download
results_claude-sonnet-4-5_anon_T_20251205_150147.json
54.8 kB
Preview
Download
results_gemini-2.5-pro_anon_T_20251127_205533.json
56.1 kB
Preview
Download
results_gemini-2.5-pro_anon_T_20251127_211005.json
55.8 kB
Preview
Download
results_gemini-2.5-pro_anon_T_20251127_212852.json
55.7 kB
Preview
Download
results_gemini-2.5-pro_anon_T_20251127_214048.json
55.5 kB
Preview
Download
results_gemini-2.5-pro_anon_T_20251127_214947.json
55.2 kB
Preview
Download
results_gemini-2.5-pro_anon_T_20251204_014415.json
55.8 kB
Preview
Download