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...

ScratchWorld - Debug — leaderboard

Metric: Success Rate (%). Source: huggingface.co. 20 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro75
2Claude Sonnet 4.575
3DeepSeek V3.275
4GPT-565
5Qwen 3 Coder 30B A3B Instruct30
6Qwen 3 VL 32B Instruct10
7Qwen 2.5 Coder 7B Instruct5
8uitars-1.5-7B0

Interactive version: theaggregate.ai/benchmark?slug=scratchworld-debug · 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.