Rational Ordering Evaluation on OR-BIAS-BENCH 400 samples (In-Distribution)
0Biasclaude-haiku-4.5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| claude-haiku-4.52026.01 | 0 | — | |
| gpt-5-mini2026.01 | 1.2 | — | |
| Qwen3-8B-OM-SFT2026.01 | 4.9 | — | |
| o4-mini2026.01 | 6.7 | — | |
| gpt-4.12026.01 | 11.8 | — | |
| Llama-3.3-70B2026.01 | 19.2 | — | |
| Qwen3-8B-Curriculum2026.01 | 20 | — |