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...

NL2Scratch — leaderboard

Metric: SAC_ref Avg (self-reported). Source: benchmarklist.com. 8 models tracked.

Top models

#ModelScore
1GPT-4.199.1
2Qwen 2.5 7B Instruct97.9
3GPT-4o Mini97.8
4Llama 3.1 8B Instruct96.5

Interactive version: theaggregate.ai/benchmark?slug=nl2scratch · 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.