List your company

Judge Performance on PERSUADE

0.955CCCGPT4o
0.09180.31590.540.7641Mar 5, 2026

Evaluation results

MethodLinks
GPT4oTest Name=synthetic_ordinal2026.030.9550.960.9440.226
Llama Maverick 4Test Name=synthetic_ordinal2026.030.9440.9530.9320.29
Llama Maverick 4Test Name=verbosity_bias_short2026.030.9420.9480.8370.4
Llama Maverick 4Test Name=verbosity_bias_long2026.030.9320.9370.9040.4
Gemini 2.5 ProTest Name=synthetic_ordinal2026.030.9270.9350.9160.344
Gemini 2.5 ProTest Name=format_invariance_22026.030.9060.9220.9010.4
GPT4oTest Name=verbosity_bias_short2026.030.8980.9360.8870.5
GPT4oTest Name=format_invariance_22026.030.8810.9650.9420.5
GPT4oTest Name=verbosity_bias_long2026.030.8770.8880.8340.6
Claude Sonnet 4.5Test Name=format_invariance_22026.030.8680.9280.9010.5
Gemini 2.5 ProTest Name=stochastic_stability2026.030.8530.8860.850.4
Gemini 2.5 ProTest Name=format_invariance_32026.030.8460.8990.9140.6
Claude Sonnet 4.5Test Name=synthetic_ordinal2026.030.8380.9010.8890.484
Llama Maverick 4Test Name=format_invariance_22026.030.8230.9050.8910.6
Claude Sonnet 4.5Test Name=format_invariance_32026.030.8190.9150.9140.6
GPT4oTest Name=semantic_paraphrase2026.030.7440.9630.9730.6
GPT4oTest Name=format_invariance_32026.030.7410.8560.8290.7
Claude Sonnet 4.5Test Name=stochastic_stability2026.030.7390.9430.9580.9
Llama Maverick 4Test Name=format_invariance_32026.030.7050.8360.8310.8
GPT4oTest Name=stochastic_stability2026.030.6820.850.8630.933
Gemini 2.5 ProTest Name=verbosity_bias_short2026.030.6820.8340.8641.1
Gemini 2.5 ProTest Name=verbosity_bias_long2026.030.6490.7710.8641.1
Llama Maverick 4Test Name=format_invariance_12026.030.6340.7090.7331
Claude Sonnet 4.5Test Name=verbosity_bias_long2026.030.6270.8340.9111.3
Claude Sonnet 4.5Test Name=verbosity_bias_short2026.030.60.9010.8461.3
Llama Maverick 4Test Name=stochastic_stability2026.030.5640.7520.7611.1
GPT4oTest Name=format_invariance_12026.030.5460.7020.7151.2
Gemini 2.5 ProTest Name=format_invariance_12026.030.4650.60.6591.3
Llama Maverick 4Test Name=semantic_paraphrase2026.030.4460.5380.5160.8
Claude Sonnet 4.5Test Name=format_invariance_12026.030.3430.5950.6161.7
Gemini 2.5 ProTest Name=semantic_paraphrase2026.030.210.4270.4681.2
Claude Sonnet 4.5Test Name=semantic_paraphrase2026.030.1250.3270.4441.2