Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Knowledge Evaluation on C-Eval (test)

93.02Natural Sciences Score

TopoPrior+ARG

52.82463.259573.69584.1305May 17, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.05
93.0292.4693.0886.6884.8386.3
2026.05
91.889.6792.5285.3382.9584.54
2026.05
91.7590.3291.7985.9683.0384.79
2026.05
91.4989.8791.985.8382.7684.42
2026.05
91.1990.5192.2785.382.7884.81
2026.05
90.8388.1591.2283.6481.6683.55
2026.05
90.6288.8490.9884.1181.0883.32
2026.05
90.3588.5291.483.4380.8282.86
2026.05
90.1689.2591.2188.0783.3285.56
2026.05
88.8286.8889.781.9279.5481.14
2026.05
88.6786.8489.7386.9281.982.36
2026.05
88.5987.6888.6486.5382.8183.79
2026.05
87.6587.188.7486.6582.1182.18
2026.05
87.6387.7289.1686.5781.8582.19
2026.05
86.8884.7587.9479.7677.3979.01
2026.05
86.6385.6288.6481.7578.3580.03
2026.05
86.5885.2188.0784.2980.2881.53
2026.05
86.5785.787.9685.5280.4481.95
2026.05
86.0386.1588.2285.9380.7982.1
2026.05
85.484.0686.5582.1279.6979.91
2026.05
84.5382.185.2780.1978.2478.41
2026.05
84.4282.5585.2978.376.5777.49
2026.05
63.5462.660.2158.1555.8257.04
2026.05
62.861.4258.9657.455.3656.01
2026.05
61.8358.7259.0556.5154.354.8
2026.05
61.1660.3558.8456.0753.9854.91
2026.05
60.8259.5257.1156.2753.8554.25
2026.05
60.458.8657.155.7953.5453.84
2026.05
59.657.8657.1554.0852.6352.96
2026.05
59.4858.1656.9354.552.0952.89
2026.05
57.4556.5956.9851.7550.5851.17
2026.05
55.8554.4755.4850.3648.0749.36
2026.05
55.1553.4256.551.3148.8449.34
2026.05
54.7353.6455.0248.6946.2548.04
2026.05
54.6153.9756.1450.849.2549.26
2026.05
54.3752.9555.8449.7247.5548.64