HumanEval+: leaderboard
HumanEval+ code-generation leaderboard from EvalPlus.
Metric: HumanEval+ pass@1 (imported). Source: evalplus.github.io. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 24 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O1 Mini (2024-09-12) | 89 | #403 |
| 2 | O1 Preview (2024-09-12) | 89 | #197 |
| 3 | GPT-4o (2024-08-06) | 87.2 | #336 |
| 4 | Qwen 2.5 Coder 32B Instruct | 87.2 | #528 |
| 5 | GPT-4 Turbo | 86.6 | #404 |
| 6 | GPT-4o Mini (2024-07-18) | 83.5 | #558 |
| 7 | Claude 3.5 Sonnet (20240620) | 81.7 | #299 |
| 8 | Grok Beta | 80.5 | #487 |
| 9 | Gemini 1.5 Pro (002) | 79.3 | #349 |
| 10 | GPT-4 | 79.3 | #438 |
| 11 | CodeQwen1.5-7B Chat | 78.7 | #1144 |
| 12 | Claude 3 Opus | 77.4 | #571 |
| 13 | OpenCoder-8B-Instruct | 77.4 | #1338 |
| 14 | Gemini 1.5 Flash (002) | 75.6 | #583 |
| 15 | Codestral-22B-v0.1 | 73.8 | #911 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=humaneval-plus · How It Works · Data refreshed daily, snapshot 2026-10-20.