List your company

Rational Ordering Evaluation on OR-BIAS-BENCH 400 samples (In-Distribution)

0Biasclaude-haiku-4.5
-0.84.61015.4Jan 28, 2026

Evaluation results

MethodLinks
claude-haiku-4.52026.010—
gpt-5-mini2026.011.2—
Qwen3-8B-OM-SFT2026.014.9—
o4-mini2026.016.7—
gpt-4.12026.0111.8—
Llama-3.3-70B2026.0119.2—
Qwen3-8B-Curriculum2026.0120—