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...

QuestBench — leaderboard

Metric: Pass Rate (%) (self-reported). Source: benchmarklist.com. 13 models tracked.

Top models

#ModelScore
1GPT-5.557.58
2Claude Opus 4.752.94
3GLM-5.135.14
4DeepSeek V4 Pro32.43
5Gemini 3.1 Pro (Preview)31.82
6Qwen 3.6 Plus30.95
7MiMo-V2.5-Pro22.73
8MiniMax-M2.716.67
9DeepSeek V3.27.81

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