Rational Ordering Evaluation on OR-BIAS-BENCH OOD 200 samples
0.036Biasclaude-haiku-4.5
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| claude-haiku-4.52026.01 | 0.036 | 0.036 | — | |
| o4-mini2026.01 | 0.077 | 0.01 | — | |
| Qwen3-8B-Curriculum2026.01 | 0.104 | -0.096 | — | |
| Qwen3-8B-OM-SFT2026.01 | 0.115 | 0.066 | — | |
| Llama-3.3-70B2026.01 | 0.125 | -0.067 | — | |
| gpt-4.12026.01 | 0.154 | 0.036 | — | |
| gpt-5-mini2026.01 | 0.533 | 0.521 | — |