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...

ClawBench v1 — leaderboard

Metric: Reward Rate (%). Source: huggingface.co. 6 models tracked.

Top models

#ModelScore
1Claude Opus 4.661.4
2Claude Sonnet 4.656.9
3Claude Haiku 4.5 (20251001)30.1
4GPT-5.4 (2026-03-05)25.5
5GPT-5.4 Mini24.8
6Kimi K2.517.6

Interactive version: theaggregate.ai/benchmark?slug=clawbench-v1 · 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.