LiveCodeBench-Plus: leaderboard
Metric: Pass@1 (%; mean of 4 attempts). Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 (Medium) | 62.6 |
| 2 | Gemini 3.1 Pro (Preview) | 59.1 |
| 3 | GPT-5.4 (Medium) | 54.1 |
| 4 | Gemini 3.5 Flash | 50 |
| 5 | Qwen 3.7 Max | 47.5 |
| 6 | Gemini 3 Flash | 40.1 |
| 7 | GPT-5.4 Mini (Medium) | 29.6 |
| 8 | DeepSeek V4 Pro (High) | 27.5 |
Interactive version: theaggregate.ai/benchmark?slug=livecodebench-plus · How It Works · Data refreshed daily, snapshot 2026-09-25.