Med-CoReasoner - MMLU-ProX-Health - Italian: leaderboard

Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.

Top models

#ModelScore
1GPT-5.2 (Low)75.98
2GPT-5.1 (Low)74.24
3GPT-4o71.47
4DeepSeek V3.269
5Claude 3.5 Haiku62.59
6Llama 3.1 70B Instruct60.84
7Qwen 2.5 72B Instruct60.26
8Qwen 2.5 32B Instruct58.95

Interactive version: theaggregate.ai/benchmark?slug=med-coreasoner-mmlu-prox-health-italian · How It Works · Data refreshed daily, snapshot 2026-09-25.