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...

LiveFMBench — leaderboard

Metric: Pass@1 Before (Pre2025) (self-reported). Source: benchmarklist.com. 11 models tracked.

Top models

#ModelScore
1DeepSeek V3.243.55
2DeepSeek V3.1 Terminus38.48
3Qwen 3 32B32.37
4DeepSeek V3 (0324)24.29
5Qwen 3 235B A22B 2507 Instruct15.83
6Llama 3.3 70B Instruct11.64

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