Med-CoReasoner - Global-MMLU-Medical - Korean: leaderboard

Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked.

Top models

#ModelScore
1GPT-5.2 (Low)83.65
2GPT-5.1 (Low)82.86
3GPT-4o81.45
4DeepSeek V3.277.54
5Qwen 2.5 72B Instruct72.96
6Qwen 2.5 32B Instruct68.17
7Llama 3.1 70B Instruct67.38
8Claude 3.5 Haiku64.25

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