MBPP+ — leaderboard
MBPP+ evaluates model capability on coding & software engineering tasks from the linked upstream source with MBPP+ pass@1 as the primary reported metric.
Metric: MBPP+ pass@1 (self-reported). Source: benchmarklist.com. Status: saturation imminent. 25 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O1 Preview | 80.2 |
| 2 | O1 Mini | 78.8 |
| 3 | Qwen 2.5 Coder 32B Instruct | 77 |
| 4 | Gemini 1.5 Pro | 74.6 |
| 5 | Claude 3.5 Sonnet (20240620) | 74.3 |
| 6 | Claude 3 Opus | 73.3 |
| 7 | GPT-4 Turbo | 73.3 |
| 8 | DeepSeek V3 | 73 |
| 9 | GPT-4o | 72.2 |
| 10 | GPT-4o Mini | 72.2 |
| 11 | OpenCoder-8B-Instruct | 71.4 |
| 12 | GPT-3.5 Turbo | 69.7 |
| 13 | Claude 3 Sonnet | 69.3 |
| 14 | Llama 3 70B Instruct | 69 |
| 15 | Claude 3 Haiku | 68.8 |
Interactive version: theaggregate.ai/benchmark?slug=mbpp-plus · How the rankings work · Data refreshed daily, snapshot 2026-07-22.