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...

EO-Gym — leaderboard

Metric: Pass@3 (self-reported). Source: benchmarklist.com. 11 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro67
2GPT-4.1 Mini64
3GPT-4.164
4Gemini 2.5 Flash63
5GPT-5.163
6Qwen 3 VL 32B Instruct59
7Qwen 3 VL 8B (Thinking)52
8Qwen 3 VL 8B Instruct49
9Qwen 3 VL 4B Instruct49
10Qwen 3 VL 4B (Thinking)49

Interactive version: theaggregate.ai/benchmark?slug=eo-gym · 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.