MLCR-AA: leaderboard
Artificial Analysis evaluates medical long-context reasoning. The overall result and separate accuracy, completeness and conciseness rates measure the quality of answers derived from the supplied medical context.
Metric: Overall Score (%). Source: artificialanalysis.ai. Saturation forecast: Around 2029. 176 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra (Max) | 41.67 | #6 (GPT-6 Astra) |
| 2 | GPT-6.1 Sol (Max) | 38.33 | #7 (GPT-6.1 Sol) |
| 3 | Kimi K3.1 Pro | 38.33 | #17 |
| 4 | GPT-6 Astra (Medium) | 38.33 | #6 (GPT-6 Astra) |
| 5 | GPT-6 Astra (xHigh) | 36.11 | #6 (GPT-6 Astra) |
| 6 | GPT-6.1 Sol (xHigh) | 35.56 | #7 (GPT-6.1 Sol) |
| 7 | Claude Haiku 5.5 (Max) | 35 | #43 (Claude Haiku 5.5) |
| 8 | GPT-6 Sol (Max) | 33.89 | #19 (GPT-6 Sol) |
| 9 | GPT-6 Astra (Low) | 33.89 | #6 (GPT-6 Astra) |
| 10 | GPT-6 Astra (High) | 32.78 | #6 (GPT-6 Astra) |
| 11 | GPT-6.1 Sol (Medium) | 32.22 | #7 (GPT-6.1 Sol) |
| 12 | GPT-6 Sol (xHigh) | 32.22 | #19 (GPT-6 Sol) |
| 13 | GPT-6.1 Sol (High) | 31.67 | #7 (GPT-6.1 Sol) |
| 14 | Qwen3.8 2.4T A95B | 30.56 | #59 |
| 15 | GPT-6.1 Terra (Max) | 30.56 | #15 (GPT-6.1 Terra) |
No result here: #3 Claude Opus 5.5, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=mlcr-aa · How It Works · Data refreshed daily, snapshot 2026-11-05.