Legal Question Answering on LEXam Interdisciplinary
70AccuracyEP-HUBO (Qwen-35B)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| EP-HUBO (Qwen-35B)Adjudicator=Opus 4.6, Trace Generator=Qwen3.5-35B2026.06 | 70 | 6.1 | |
| EP-HUBO (OSS-20B)Adjudicator=Opus 4.6, Trace Generator=OSS-20B2026.06 | 69.8 | 5.9 | |
| MV (Qwen-35B)Trace Generator=Qwen3.5-35B2026.06 | 67 | — | |
| ZS (no traces/HUBO)Adjudicator=Opus 4.62026.06 | 64 | — | |
| MV (OSS-20B)Trace Generator=OSS-20B2026.06 | 45.3 | — | |
| EP-HUBO (Qwen-35B)Adjudicator=Sonnet 4.6, Trace Generator=Qwen3.5-35B2026.06 | 37 | 22.3 | |
| EP-HUBO (OSS-20B)Adjudicator=Sonnet 4.6, Trace Generator=OSS-20B2026.06 | 26.9 | 12.1 | |
| ZS (no traces/HUBO)Adjudicator=Sonnet 4.62026.06 | 14.8 | — |