HumanEval
AI 基准测试结果和模型表现
类型: percentage
已记录的结果
82
平均分数
82.66%
分数范围
39.70% - 92.90%
领先模型
92.90% - Mistral Small 3.2
分数变化趋势
按日期绘制的单项基准测试分数。
模型结果
| 组织 | 模型 | 报告时间 | 最高分数 | 信息 | 自行报告 | 来源 |
|---|---|---|---|---|---|---|
| Mistral Small 3.2 | 2025年6月20日 | 92.90% | Pass@5 | 是 | 来源 | |
| o1 mini | 2024年9月12日 | 92.40% | - | 是 | 来源 | |
| Mistral Large 2.1 | 2024年11月18日 | 92% | inferred version-family alias from mistral-large-2-2407 | 是 | 来源 | |
| Mistral OCR 2 | 2025年5月22日 | 92% | inferred family alias from mistral-large-2-2407 (score=0.3100; benches=5) | 是 | 来源 | |
| Qwen 2.5 Coder 32B Instruct | - | 91.50% | inferred high-confidence family alias from qwen2.5-vl-32b (score=0.4641; benches=28) | 是 | 来源 | |
| Qwen 2.5 VL 32B Instruct | 2025年3月24日 | 91.50% | - | 是 | 来源 | |
| Qwen 2.5 VL 3B Instruct | - | 91.50% | inferred high-confidence family alias from qwen2.5-vl-32b (score=0.4914; benches=28) | 是 | 来源 | |
| GPT 4o (2024-05-13) | 2024年5月13日 | 90.20% | - | 是 | 来源 | |
| Granite 3.0 8B Instruct | - | 89.73% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.4911; benches=14) | 是 | 来源 | |
| Granite 3.1 8B Instruct | - | 89.73% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.4911; benches=14) | 是 | 来源 | |
| Granite 3.2 8B Instruct | - | 89.73% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.4911; benches=14) | 是 | 来源 | |
| Granite 3.2 8B Instruct Preview | - | 89.73% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.4687; benches=14) | 是 | 来源 | |
| Granite 3.3 2B Instruct | 2025年4月16日 | 89.73% | inferred family alias from granite-3.3-8b-instruct (score=0.3627; benches=14) | 是 | 来源 | |
| Granite 3.3 8B Instruct | 2025年4月16日 | 89.73% | - | 是 | 来源 | |
| Granite Guardian 3.0 8B | - | 89.73% | inferred family alias from granite-3.3-8b-instruct (score=0.4062; benches=14) | 是 | 来源 | |
| Granite Guardian 3.1 8B | - | 89.73% | inferred family alias from granite-3.3-8b-instruct (score=0.4062; benches=14) | 是 | 来源 | |
| Granite Guardian 3.3 8B | - | 89.73% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.5071; benches=14) | 是 | 来源 | |
| Granite Speech 3.2 8B | - | 89.73% | inferred family alias from granite-3.3-8b-instruct (score=0.4062; benches=14) | 是 | 来源 | |
| Granite Speech 3.3 8B | - | 89.73% | inferred high-confidence family alias from granite-3.3-8b-instruct (score=0.5071; benches=14) | 是 | 来源 | |
| Gemini Diffusion | 2025年5月20日 | 89.60% | Pass@1 | 是 | 来源 | |
| DeepSeek V2.5 (2024-09-05) | 2024年9月05日 | 89% | inferred alias from deepseek-v2.5 | 是 | 来源 | |
| DeepSeek V2.5 (2024-12-10) | 2024年12月10日 | 89% | inferred alias from deepseek-v2.5 | 是 | 来源 | |
| Granite 4.1 30B | 2026年4月29日 | 88.41% | pass@1 | 是 | 来源 | |
| LongCat Flash Chat | - | 88.41% | inferred high-confidence family alias from longcat-flash-chat (score=0.4667; benches=16) | 是 | 来源 | |
| Llama 2 70B Chat | 2023年6月20日 | 88.40% | inferred family alias from llama-3.3-70b-instruct (score=0.3129; benches=9) | 是 | 来源 |
