Skip to content
The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps Task Explorer Builder
How It Works About Guesswork Metrics
The Aggregate
Loading data...

HELM Arabic - Arabic Exams: leaderboard

Metric: EM. Source: crfm.stanford.edu. 41 models tracked.

Top models

#ModelScore
1Llama 3.3 70B Instruct67.91
2Claude Opus 4.765.14
3Claude Sonnet 4.663.76
4Gemini 2.5 Flash (Thinking)63.24
5GPT-5.4 (2026-03-05)62.97
6GPT-4.1 (2025-04-14)62.38
7Qwen 3.5 397B A17B62.23
8Gemma 4 31B (IT)61.66
9Gemini 2.5 Flash Lite (Thinking)61.5
10Qwen 3 Next 80B A3B Instruct60.79
11Llama 4 Maverick Instruct FP860.25
12Llama 4 Scout Instruct59.95
13Claude Haiku 4.5 (20251001)59.4
14Qwen3 235B A22B Instruct 2507 FP859
15Qwen 2.5 72B Instruct58.85

Interactive version: theaggregate.ai/benchmark?slug=helm-arabic-arabic-exams · How It Works · Data refreshed daily, snapshot 2026-09-08.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.
A

Your Aggregate

Sign in to keep your work

Save custom rankings and get 50 free task analyses each day.

Continue with Google Continue with GitHub

No password to remember. Your public profile identifies saved work.

Your Aggregate

Account

  • Saved custom aggregate views
  • 50 free task analyses per day
Sign out