Baichuan-M3: benchmark results
Provider: Baichuan.
Aggregate Rating 1711 ± 42, rank #297 of 10916 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ClinConsensus - Lay-Facing | 31 | CACS@10 (%; GPT-5.1 rubric judge, lay-facing cases) | 90 |
| LiveMedBench | 25.61 | Overall Score (%) | 89.2 |
| ClinConsensus - Professional-Facing | 25.7 | CACS@10 (%; GPT-5.1 rubric judge, professional-facing cases) | 70 |
| LogiMed-RoB - Atomic Consistency | 46.84 | Fully consistent instances (%) | 55.6 |
| LogiMed-RoB - Condition-Aware Ratio | 94.02 | Ratio (%) | 55.6 |
| LogiMed-RoB - Domain Logical Fidelity | 72.55 | Fidelity (%) | 44.4 |
| LogiMed-RoB - End-to-End Consistency | 11.58 | Fully consistent instances (%) | 44.4 |
| LogiMed-RoB - Verdict Reliability | 99.3 | Reliability (%) | 22.2 |
Interactive version: theaggregate.ai/model?slug=baichuan-m3 · How It Works · Data refreshed daily, snapshot 2026-11-08.