LiveCodeBench — leaderboard
Contamination-free code benchmark using fresh problems from LeetCode, AtCoder, and CodeForces. Tests code generation, self-repair, execution, and test prediction.
Metric: Pass@1 avg (%). Source: livecodebench.github.io. Status: saturated. 28 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O4 Mini (High) | 87.3 |
| 2 | O3 (High) | 84.7 |
| 3 | O4 Mini (Medium) | 84.5 |
| 4 | DeepSeek R1 0528 | 84.4 |
| 5 | Gemini 2.5 Pro (Preview 06-05) | 84.3 |
| 6 | Qwen 3 235B A22B | 80.4 |
| 7 | Grok 3 Mini (High) | 78.1 |
| 8 | O3 Mini (2025-01-31) (High) | 77.7 |
| 9 | O4 Mini (Low) | 77.4 |
| 10 | Gemini 2.5 Flash (Preview 05-20) | 76.2 |
| 11 | O3 Mini (2025-01-31) | 75.4 |
| 12 | Gemini 2.5 Flash (Preview 04-17) | 75.1 |
| 13 | O3 Mini (Low) | 70.6 |
| 14 | Claude Opus 4 (Thinking) | 70.4 |
| 15 | Claude Sonnet 4 (Thinking) | 68.5 |
Interactive version: theaggregate.ai/benchmark?slug=livecodebench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.