Skip to content

The Aggregate

Unified LLM rankings, daily

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

AA Global-MMLU-Lite - Yoruba — leaderboard

Metric: Accuracy (%). Source: artificialanalysis.ai. 112 models tracked.

Top models

#ModelScore
1Gemini 3.1 Pro (Preview)88.75
2Gemini 3 Pro (Preview) (High)86.25
3Claude Opus 4.6 (Adaptive Reasoning, Max Effort)83.5
4Claude Opus 4.5 (Thinking)83
5GPT-5 (High)82.83
6Gemini 2.5 Pro81.42
7GPT-5.1 (High)81.42
8GPT-5 (Medium)80.67
9Claude Opus 4.5 (Non-reasoning)80.67
10GPT-5.1 Codex (High)79.75
11Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)79.58
12Grok 478.5
13GPT-5.2 (Medium)78.08
14GPT-5.4 Mini (xHigh)78
15Grok 4.20 0309 (Reasoning)75.92

Interactive version: theaggregate.ai/benchmark?slug=aa-global-mmlu-lite-yoruba · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

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