EvalPlus — leaderboard
EvalPlus leaderboard aggregating HumanEval+ and MBPP+ code-generation pass@1 scores.
Metric: EvalPlus Avg. (self-reported). Source: benchmarklist.com. Status: saturation imminent. 25 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O1 Preview | 84.6 |
| 2 | O1 Mini | 83.9 |
| 3 | Qwen 2.5 Coder 32B Instruct | 82.1 |
| 4 | DeepSeek V3 | 79.8 |
| 5 | GPT-4o | 79.7 |
| 6 | Claude 3.5 Sonnet (20240620) | 78 |
| 7 | GPT-4o Mini | 77.85 |
| 8 | GPT-4 Turbo | 77.5 |
| 9 | Gemini 1.5 Pro | 76.95 |
| 10 | Claude 3 Opus | 75.35 |
| 11 | OpenCoder-8B-Instruct | 74.4 |
| 12 | Grok Beta | 73.05 |
| 13 | Gemini 1.5 Flash | 71.55 |
| 14 | Llama 3 70B Instruct | 70.5 |
| 15 | GPT-3.5 Turbo | 70.2 |
Interactive version: theaggregate.ai/benchmark?slug=evalplus · How the rankings work · Data refreshed daily, snapshot 2026-07-22.