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

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

Top models

#ModelScore
1GPT-5.2 (Low)73.94
2GPT-5.1 (Low)70.45
3GPT-4o67.39
4DeepSeek V3.266.81
5Claude 3.5 Haiku57.64
6Qwen 2.5 72B Instruct56.48
7Qwen 2.5 32B Instruct54.73
8Llama 3.1 70B Instruct48.33

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