Baichuan-M1-14B: benchmark results
Provider: Baichuan.
Aggregate Rating 1618 ± 49, rank #851 of 10916 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLMEval-Med - Medical Safety and Ethics | 70.03 | Usability rate: share of responses a GPT-4o judge scores 4 o | 100 |
| PsychEthicsBench - Ethical Behavior | 78.29 | Overall ethical rate (%; share of 2,612 open-ended answers t | 91.7 |
| PsychEthicsBench - Ethical Knowledge | 77.78 | Exact match (%; 1,377 single- and multiple-answer questions | 91.7 |
| LLMEval-Med - Medical Knowledge | 62.88 | Usability rate: share of responses a GPT-4o judge scores 4 o | 75 |
| Active Evidence-Seeking and Diagnostic Reasoni | 44.9 | Task 2: Active Seeking Exact Accuracy (self-reported) | 71.4 |
| LLMEval-Med - Medical Text Generation | 48.45 | Usability rate: share of responses physicians rate usable on | 58.3 |
| LLMEval-Med - Medical Reasoning | 55.23 | Usability rate: share of responses a GPT-4o judge scores 4 o | 54.2 |
| LLMEval-Med | 55.43 | Overall usability: mean of the five category usability rates | 44.4 |
| LLMEval-Med - Medical Language Understanding | 40.53 | Usability rate: share of responses a GPT-4o judge scores 4 o | 16.7 |
Interactive version: theaggregate.ai/model?slug=baichuan-m1-14b · How It Works · Data refreshed daily, snapshot 2026-11-08.