Skip to content
The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps Task Explorer Builder
How It Works Guesswork Metrics
The Aggregate
Loading data...

HumanCLAW-Bench - Find — leaderboard

Metric: Success Rate (%). Source: human-claw.github.io. 9 models tracked.

Top models

#ModelScore
1Gemma 4 31B58.1
2GPT-5.555.8
3Qwen 3.6 27B51
4Qwen 3.6 35B A3B44.6
5Qwen 3.5 27B37.8

Interactive version: theaggregate.ai/benchmark?slug=humanclaw-bench-find · How It Works · Data refreshed daily, snapshot 2026-08-05.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.