List your company

Human Preference Evaluation on Oral Argument Simulation (Evaluation set)

72WinsGemini-2.5-Pro
22.0835.044860.96Mar 5, 2026

Evaluation results

MethodLinks
Gemini-2.5-ProSimulation Mode=AGENT2026.0372312555.615.8
Llama-3.3-70B-InstructSimulation Mode=PROMPT2026.0366373454.69.9
GPT-4oSimulation Mode=PROMPT2026.03624631518.6
Gemini-2.5-ProSimulation Mode=PROMPT2026.0362412649.315.1
Ground Truth2026.0346553341.111.8
GPT-4oSimulation Mode=AGENT2026.0345523240.115.1
Qwen3-32BSimulation Mode=PROMPT2026.0342582435.518.4
GPT-OSS-120BSimulation Mode=PROMPT2026.0336602832.918.4
GPT-OSS-120BSimulation Mode=AGENT2026.0324751721.423.7