MMLU-CF 0-shot Validation: leaderboard

MMLU-CF 0-shot Validation — Official MMLU-CF contamination-free benchmark; 0-shot validation cohort. Original MMLU column and test-minus-validation deltas are not independent capability panels. Native API/checkpoint labels retained. Metric: Accuracy (%). Source: https://github.com/microsoft/MMLU-CF

Metric: Accuracy (%). Source: github.com. Saturation forecast: Estimated already saturated. 44 models tracked. Updated 16 Nov 2026.

Top models

#ModelScoreOverall rank
1GPT-4o72.4#744
2Qwen 2.5 72B Instruct70.4#1095
3Llama 3.1 70B Instruct69.7#1542
4phi-4-14B69.4#1666
5Qwen 2.5 32B Instruct68.8#1232
6GPT-4 Turbo68.7#999
7Llama 3.3 70B Instruct67.5#1379
8Llama 3 70B Instruct67.4#1689
9Qwen 2.5 14B Instruct66#1750
10GPT-4o Mini65.3#1658
11Mixtral 8x22B Instruct64.8#2097
12Gemma 2 27B64#2141
13Phi-3-medium-128k-instruct62.7#3321
14Qwen 2 72B Instruct62.5#1514
15Phi-3.5-MoE-instruct62.1#2199

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=mmlu-cf-0-shot-validation · How It Works · Data refreshed daily, snapshot 2026-11-16.