Med-CoReasoner - MMLU-ProX-Health - Italian: leaderboard
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 (Low) | 75.98 |
| 2 | GPT-5.1 (Low) | 74.24 |
| 3 | GPT-4o | 71.47 |
| 4 | DeepSeek V3.2 | 69 |
| 5 | Claude 3.5 Haiku | 62.59 |
| 6 | Llama 3.1 70B Instruct | 60.84 |
| 7 | Qwen 2.5 72B Instruct | 60.26 |
| 8 | Qwen 2.5 32B Instruct | 58.95 |
Interactive version: theaggregate.ai/benchmark?slug=med-coreasoner-mmlu-prox-health-italian · How It Works · Data refreshed daily, snapshot 2026-09-25.