MBPP+: leaderboard
378 hand-verified Python problems drawn from MBPP-sanitized, each with 35x more test cases than the original MBPP, built by the EvalPlus project (NeurIPS 2023); pass@1 with greedy decoding.
Metric: MBPP+ pass@1 (self-reported). Source: benchmarklist.com. Status: saturated. 25 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O1 Mini (2024-09-12) | 78.8 |
| 2 | Qwen 2.5 Coder 32B Instruct | 77 |
| 3 | Gemini 1.5 Pro (002) | 74.6 |
| 4 | Claude 3.5 Sonnet (20240620) | 74.3 |
| 5 | Claude 3 Opus | 73.3 |
| 6 | GPT-4 Turbo (Preview) | 73.3 |
| 7 | GPT-4o Mini (2024-07-18) | 72.2 |
| 8 | GPT-4o (2024-08-06) | 72.2 |
| 9 | OpenCoder-8B-Instruct | 71.4 |
| 10 | GPT-3.5 Turbo (1106) | 69.7 |
| 11 | Claude 3 Sonnet | 69.3 |
| 12 | Llama 3 70B Instruct | 69 |
| 13 | Claude 3 Haiku | 68.8 |
| 14 | Gemini 1.5 Flash (002) | 67.5 |
Interactive version: theaggregate.ai/benchmark?slug=mbpp-plus · How It Works · Data refreshed daily, snapshot 2026-09-05.