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. Saturation forecast: Estimated already saturated. 28 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O4 Mini (High) | 87.3 | #180 (O4 Mini) |
| 2 | O3 (High) | 84.7 | #124 (O3) |
| 3 | O4 Mini (Medium) | 84.5 | #180 (O4 Mini) |
| 4 | DeepSeek R1 0528 | 84.4 | #222 |
| 5 | Gemini 2.5 Pro (Preview 06-05) | 84.3 | #106 |
| 6 | Gemini 2.5 Pro (Preview 05-06) | 82.7 | #147 |
| 7 | Qwen 3 235B A22B | 80.4 | #313 |
| 8 | Grok 3 Mini (High) | 78.1 | #281 (Grok 3 Mini) |
| 9 | O3 Mini (2025-01-31) (High) | 77.7 | #240 (O3 Mini (2025-01-31)) |
| 10 | O4 Mini (Low) | 77.4 | #180 (O4 Mini) |
| 11 | Gemini 2.5 Flash (Preview 05-20) | 76.2 | #216 |
| 12 | O3 Mini (2025-01-31) | 75.4 | #240 |
| 13 | Gemini 2.5 Flash (Preview 04-17) | 75.1 | #237 |
| 14 | O3 Mini (Low) | 70.6 | #272 (O3 Mini) |
| 15 | Claude Opus 4 (Thinking) | 70.4 | #163 (Claude Opus 4) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=livecodebench · How It Works · Data refreshed daily, snapshot 2026-10-20.