MLCR-AA - Accuracy: 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: Accuracy (%). Source: artificialanalysis.ai. Saturation forecast: Around February 2027. 176 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Terra (Max) | 98.33 | #15 (GPT-6.1 Terra) |
| 2 | GPT-6.1 Sol (Max) | 96.67 | #7 (GPT-6.1 Sol) |
| 3 | GPT-6 Astra (Max) | 95.56 | #6 (GPT-6 Astra) |
| 4 | GPT-6 Astra (xHigh) | 95 | #6 (GPT-6 Astra) |
| 5 | GPT-6 Sol (Medium) | 95 | #19 (GPT-6 Sol) |
| 6 | GPT-6 Sol (High) | 94.44 | #19 (GPT-6 Sol) |
| 7 | Kimi K3.1 Pro | 93.89 | #17 |
| 8 | GPT-6 Astra (High) | 93.89 | #6 (GPT-6 Astra) |
| 9 | GPT-6.1 Sol (xHigh) | 93.89 | #7 (GPT-6.1 Sol) |
| 10 | GPT-6 Sol (xHigh) | 93.33 | #19 (GPT-6 Sol) |
| 11 | GPT-6 Astra (Medium) | 92.22 | #6 (GPT-6 Astra) |
| 12 | GPT-6 Sol (Max) | 91.67 | #19 (GPT-6 Sol) |
| 13 | GPT-6 Astra (Low) | 91.67 | #6 (GPT-6 Astra) |
| 14 | GPT-6.1 Sol (High) | 90.56 | #7 (GPT-6.1 Sol) |
| 15 | GPT-6.1 Sol (Medium) | 90.56 | #7 (GPT-6.1 Sol) |
No result here: #3 Claude Opus 5.5, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=mlcr-aa-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-05.