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...

A2RBench — leaderboard

Metric: Total Acc (self-reported). Source: benchmarklist.com. 14 models tracked.

Top models

#ModelScore
1GPT-539
2GPT-5 Mini36.9
3O4 Mini33.7
4Claude Sonnet 4.530.6
5GPT-5.228.3
6Gemini 2.5 Flash27.7
7GLM-4.621
8DeepSeek V3.220.8
9Qwen 3 32B19.3
10GPT-4o Mini16.1
11Qwen 3 14B14.2
12Gemini 3 Flash (Preview)13.1
13Qwen 3 8B0

Interactive version: theaggregate.ai/benchmark?slug=a2rbench · 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.