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...

MageBench S2 — leaderboard

Metric: Rating. Source: mage-bench.com. 11 models tracked.

Top models

#ModelScore
1GPT-5.4 Mini (Medium)1617
2DeepSeek V3.21616
3Mistral Medium 3.11616
4Gemini 3.1 Flash Lite1599
5Qwen 3 235B A22B1584

Interactive version: theaggregate.ai/benchmark?slug=magebench-s2 · 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.