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...

Merge-Bench — leaderboard

Metric: Equivalent text (self-reported). Source: benchmarklist.com. 18 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro54.7
2O3 Pro46.1
3Claude Opus 444.4
4Grok 433.4
5QwQ-32B32.1
6Qwen 3 235B A22B30.9
7Llama 4 Maverick26.2
8Qwen 3 32B13.2
9Qwen 3 14B12.9
10Qwen 3 8B5.5

Interactive version: theaggregate.ai/benchmark?slug=merge-bench · 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.