Bedside Bench: leaderboard
Physician-authored clinical cases in ten suites from differential diagnosis to medication safety, graded by an LLM judge against the authors' criteria; the score is the macro-average of suite means over 3 Fireworks runs of 500 cases. Answers are free-text case work, not exam multiple choice.
Metric: Macro-average of 10 suite means, 3 runs of 500 cases (%). Source: fireworks.ai. Saturation forecast: Estimated already saturated. 15 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 5 | Max | 94.6 | #20 |
| 2 | Muse Spark Open | Max | 94.3 | #81 |
| 3 | GPT-6.1 Sol | Max | 93.9 | #10 |
| 4 | GPT-6 Astra | xHigh | 93.4 | #6 |
| 5 | Gemini 4 Argon | High | 92.7 | #12 |
| 6 | Kimi K3.1 Pro | Max | 91.46 | #29 |
| 7 | Kimi K3 | Max | 89.7 | #56 |
| 8 | Ember-1 | Max | 89.1 | #84 |
| 9 | GPT-6 Sol | xHigh | 88.1 | #26 |
| 10 | GPT-6 Luna | xHigh | 87.2 | #99 |
| 11 | GLM-5.3 | Max | 86.9 | #68 |
| 12 | Gemini 3.8 Flash | High | 86.5 | #36 |
| 13 | Grok 4.6 | xHigh | 83.3 | #45 |
| 14 | DeepSeek V4.1 Flash | Max | 82.9 | #62 |
| 15 | DeepSeek V4 Pro (0813) | Max | 80.6 | #90 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=bedside-bench · How It Works · Data refreshed daily, snapshot 2026-11-16.