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...

RepoMirage — leaderboard

Metric: Avg. (self-reported). Source: benchmarklist.com. 8 models tracked.

Top models

#ModelScore
1Gemini 3.1 Pro (Preview)41.4
2DeepSeek V3.239.8
3Claude Sonnet 4.628.2
4GPT-527.6
5Qwen 3.6 35B A3B24.2
6Qwen3 Coder Next22.6
7MiniMax-M2.714.8
8GPT-4.13.4

Interactive version: theaggregate.ai/benchmark?slug=repomirage · 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.