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...

WMT25 English-Maasai ESA — leaderboard

Metric: ESA Human Score. Source: github.com. 18 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro9.8
2aya-expanse-8B6
3Llama 4 Maverick5.2
4aya-expanse-32B3.1
5Llama 3.1 8B3
6Gemma 3 12B3
7DeepSeek V33
8Qwen 2.5 7B2.8
9Qwen 3 235B A22B2.7

Interactive version: theaggregate.ai/benchmark?slug=wmt25-english-maasai-esa · 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.