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

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

Top models

#ModelScore
1GPT-5.2 (Low)70.6
2GPT-5.1 (Low)67.89
3GPT-4o61.86
4DeepSeek V3.251.67
5Llama 3.1 70B Instruct44.25
6Claude 3.5 Haiku35.81
7Qwen 2.5 72B Instruct30.13
8Qwen 2.5 32B Instruct26.76

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