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...

TW-LegalBench — leaderboard

Metric: Total (self-reported). Source: benchmarklist.com. 13 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.581
2GPT-576.7
3GPT-5.273.9
4Qwen 3 235B A22B69.1
5GPT-4o66.2
6Llama 3.1 405B Instruct60.5
7GPT-OSS-120B56
8nemotron-3-nano-30B-a3B52.6
9Qwen 2.5 7B49.7
10GPT-OSS-20B48.3

Interactive version: theaggregate.ai/benchmark?slug=tw-legalbench · 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.