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...

LiveCodeBench Pro Hard — leaderboard

Metric: Pass@1 (%). Source: livecodebenchpro.com. 6 models tracked.

Top models

#ModelScore
1O4 Mini (2025-04-16) (High)1.43
2Claude Sonnet 4.5 (Thinking)0
3Qwen 3 Next 80B A3B (Thinking)0
4DeepSeek R1 05280

Interactive version: theaggregate.ai/benchmark?slug=livecodebench-pro-hard · 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.