HELM Arabic - Mbzuai Human Translated Arabic Mmlu - College Computer Science Leaderboard · The Aggregate

HELM Arabic - Mbzuai Human Translated Arabic Mmlu - College Computer Science: leaderboard

Metric: Exact Match (%). Source: crfm.stanford.edu. 41 models tracked.

Top models

#	Model	Score
1	Claude Opus 4.7	81
2	GPT-5.4 (2026-03-05)	79
3	Gemma 4 31B (IT)	77
4	Claude Sonnet 4.6	74
5	Qwen 3 Next 80B A3B Instruct	74
6	Qwen 3.5 397B A17B	73
7	Mistral Large 3	73
8	Gemini 2.5 Flash (Thinking)	72
9	Gemini 2.5 Flash Lite (Thinking)	72
10	GPT-4.1 (2025-04-14)	71
11	Claude Haiku 4.5 (20251001)	71
12	Llama 4 Maverick Instruct FP8	68
13	DeepSeek V3.1	64
14	Mistral Large 2 (Nov) Instruct (2411)	64
15	Qwen 3.5 9B	60

Interactive version: theaggregate.ai/benchmark?slug=helm-arabic-mbzuai-human-translated-arabic-mmlu-college-computer-science · How It Works · Data refreshed daily, snapshot 2026-09-19.