Med-CoReasoner - Global-MMLU-Medical - Italian: leaderboard
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 (Low) | 85.78 |
| 2 | GPT-5.1 (Low) | 85.77 |
| 3 | GPT-4o | 82.46 |
| 4 | DeepSeek V3.2 | 81.33 |
| 5 | Qwen 2.5 72B Instruct | 78.6 |
| 6 | Llama 3.1 70B Instruct | 78.14 |
| 7 | Qwen 2.5 32B Instruct | 75.08 |
| 8 | Claude 3.5 Haiku | 72.58 |
Interactive version: theaggregate.ai/benchmark?slug=med-coreasoner-global-mmlu-medical-italian · How It Works · Data refreshed daily, snapshot 2026-09-25.