热度56.1▲ 1.0
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 | 95.5% | pass@1 | 2026-08-28 |
| #2 | O1 Mini (Sept 2024) | MBPP evalplus | 93.1% | pass@1 | 2026-08-28 |
| #3 | Qwen2.5-Coder-32B-Instruct Qwen | MBPP evalplus | 90.5% | pass@1 | 2026-08-28 |
| #4 | Gemini 1.5 Pro 002 | MBPP evalplus | 89.7% | pass@1 | 2026-08-28 |
| #5 | DeepSeek-Coder-V2-Instruct deepseek-ai | MBPP evalplus | 89.4% | pass@1 | 2026-08-28 |
| #6 | Claude Sonnet 3.5 (June 2024) | MBPP evalplus | 89.4% | pass@1 | 2026-08-28 |
| #7 | claude-3-opus (Mar 2024) | MBPP evalplus | 89.4% | pass@1 | 2026-08-28 |
| #8 | DeepSeek-V3 (Nov 2024) deepseek-ai | MBPP evalplus | 87.6% | pass@1 | 2026-08-28 |
| #9 | DeepSeek-V2.5 (Nov 2024) deepseek-ai | MBPP evalplus | 87.6% | pass@1 | 2026-08-28 |
| #10 | GPT 4o (Aug 2024) | MBPP evalplus | 87.6% | pass@1 | 2026-08-28 |
| #11 | Grok Beta | MBPP evalplus | 86% | pass@1 | 2026-08-28 |
| #12 | GPT-4-Turbo (Nov 2023) | MBPP evalplus | 85.7% | pass@1 | 2026-08-28 |
| #13 | GPT 4o Mini (July 2024) | MBPP evalplus | 85.4% | pass@1 | 2026-08-28 |
| #14 | Gemini 1.5 Flash 002 | MBPP evalplus | 84.7% | pass@1 | 2026-08-28 |
| #15 | claude-3-sonnet (Mar 2024) | MBPP evalplus | 83.6% | pass@1 | 2026-08-28 |
| #16 | GPT-3.5-Turbo (Nov 2023) | MBPP evalplus | 82.5% | pass@1 | 2026-08-28 |
| #17 | Llama3-70B-instruct meta-llama | MBPP evalplus | 82.3% | pass@1 | 2026-08-28 |
| #18 | OpenCoder-8B-Instruct infly | MBPP evalplus | 82% | pass@1 | 2026-08-28 |
| #19 | Artigenz-Coder-DS-6.7B Artigenz | MBPP evalplus | 80.7% | pass@1 | 2026-08-28 |
| #20 | DeepSeek-Coder-33B-instruct deepseek-ai | MBPP evalplus | 80.4% | pass@1 | 2026-08-28 |
| #21 | OpenCodeInterpreter-DS-33B m-a-p | MBPP evalplus | 80.2% | pass@1 | 2026-08-28 |
| #22 | claude-3-haiku (Mar 2024) | MBPP evalplus | 80.2% | pass@1 | 2026-08-28 |
| #23 | CodeQwen1.5-7B-Chat Qwen | MBPP evalplus | 79.4% | pass@1 | 2026-08-28 |
| #24 | Magicoder-S-DS-6.7B ise-uiuc | MBPP evalplus | 79.4% | pass@1 | 2026-08-28 |
| #25 | WhiteRabbitNeo-33B-v1 WhiteRabbitNeo | MBPP evalplus | 79.4% | pass@1 | 2026-08-28 |
89 条结果 · 当前 1-25
1 / 4