LiveCodeBench Pro Medium: leaderboard
Metric: Pass@1 (%). Source: livecodebenchpro.com. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 (High) | 52.11 |
| 2 | GPT-5 (High) | 40.85 |
| 3 | O4 Mini (2025-04-16) (High) | 29.23 |
| 4 | Qwen 3 Next 80B A3B (Thinking) | 7.04 |
| 5 | DeepSeek R1 0528 | 1.41 |
| 6 | Claude Sonnet 4.5 (Thinking) | 0 |
Interactive version: theaggregate.ai/benchmark?slug=livecodebench-pro-medium · How It Works · Data refreshed daily, snapshot 2026-09-05.