热度8.5▼ 0.3
MBPP+
evalplus / pass@1 · 89 行结果
| 排名 | 模型 | 子项 | 分数 | Metric | 时间 |
|---|---|---|---|---|---|
| #1 | O1 Preview (Sept 2024) | MBPP+ evalplus | 80.2% | pass@1 | 2026-08-28 |
| #2 | O1 Mini (Sept 2024) | MBPP+ evalplus | 78.8% | pass@1 | 2026-08-28 |
| #3 | Qwen2.5-Coder-32B-Instruct Qwen | MBPP+ evalplus | 77% | pass@1 | 2026-08-28 |
| #4 | DeepSeek-Coder-V2-Instruct deepseek-ai | MBPP+ evalplus | 75.1% | pass@1 | 2026-08-28 |
| #5 | Gemini 1.5 Pro 002 | MBPP+ evalplus | 74.6% | pass@1 | 2026-08-28 |
| #6 | Claude Sonnet 3.5 (June 2024) | MBPP+ evalplus | 74.3% | pass@1 | 2026-08-28 |
| #7 | DeepSeek-V2.5 (Nov 2024) deepseek-ai | MBPP+ evalplus | 74.1% | pass@1 | 2026-08-28 |
| #8 | GPT-4-Turbo (Nov 2023) | MBPP+ evalplus | 73.3% | pass@1 | 2026-08-28 |
| #9 | claude-3-opus (Mar 2024) | MBPP+ evalplus | 73.3% | pass@1 | 2026-08-28 |
| #10 | DeepSeek-V3 (Nov 2024) deepseek-ai | MBPP+ evalplus | 73% | pass@1 | 2026-08-28 |
| #11 | GPT 4o (Aug 2024) | MBPP+ evalplus | 72.2% | pass@1 | 2026-08-28 |
| #12 | GPT 4o Mini (July 2024) | MBPP+ evalplus | 72.2% | pass@1 | 2026-08-28 |
| #13 | OpenCoder-8B-Instruct infly | MBPP+ evalplus | 71.4% | pass@1 | 2026-08-28 |
| #14 | DeepSeek-Coder-33B-instruct deepseek-ai | MBPP+ evalplus | 70.1% | pass@1 | 2026-08-28 |
| #15 | GPT-3.5-Turbo (Nov 2023) | MBPP+ evalplus | 69.7% | pass@1 | 2026-08-28 |
| #16 | Artigenz-Coder-DS-6.7B Artigenz | MBPP+ evalplus | 69.6% | pass@1 | 2026-08-28 |
| #17 | claude-3-sonnet (Mar 2024) | MBPP+ evalplus | 69.3% | pass@1 | 2026-08-28 |
| #18 | CodeQwen1.5-7B-Chat Qwen | MBPP+ evalplus | 69% | pass@1 | 2026-08-28 |
| #19 | Llama3-70B-instruct meta-llama | MBPP+ evalplus | 69% | pass@1 | 2026-08-28 |
| #20 | Magicoder-S-DS-6.7B ise-uiuc | MBPP+ evalplus | 69% | pass@1 | 2026-08-28 |
| #21 | claude-3-haiku (Mar 2024) | MBPP+ evalplus | 68.8% | pass@1 | 2026-08-28 |
| #22 | OpenCodeInterpreter-DS-33B m-a-p | MBPP+ evalplus | 68.5% | pass@1 | 2026-08-28 |
| #23 | Gemini 1.5 Flash 002 | MBPP+ evalplus | 67.5% | pass@1 | 2026-08-28 |
| #24 | WhiteRabbitNeo-33B-v1 WhiteRabbitNeo | MBPP+ evalplus | 66.9% | pass@1 | 2026-08-28 |
| #25 | OpenCodeInterpreter-DS-6.7B m-a-p | MBPP+ evalplus | 66.4% | pass@1 | 2026-08-28 |
89 条结果 · 当前 1-25
1 / 4