热度25.4▼ 0.5
SWE-bench Multimodal
swe-bench / resolved · 22 行结果
| 排名 | 模型 | 子项 | 分数 | Metric | 时间 |
|---|---|---|---|---|---|
| #1 | o3 OpenAIGUIRepair + o3 (2025-04-16) | SWE-bench Multimodal swe-bench | 36% | resolved | 2025-07-01 |
| #2 | o3 OpenAICodefuse_Pycfuse_SVR | SWE-bench Multimodal swe-bench | 36% | resolved | 2025-11-17 |
| #3 | Claude 4 Sonnet AnthropicRefact.ai Agent | SWE-bench Multimodal swe-bench | 35.6% | resolved | 2025-06-11 |
| #4 | Claude Sonnet 4 AnthropicOpenHands-Versa (Claude-Sonnet 4) | SWE-bench Multimodal swe-bench | 34.4% | resolved | 2025-05-28 |
| #5 | o4-mini OpenAIGUIRepair + o4-mini (2025-04-16) | SWE-bench Multimodal swe-bench | 33.9% | resolved | 2025-05-31 |
| #6 | Claude 3.7 Sonnet AnthropicOpenHands-Versa (Claude-3.7 Sonnet) | SWE-bench Multimodal swe-bench | 31.3% | resolved | 2025-05-09 |
| #7 | GPT-4.1 OpenAIGUIRepair + GPT 4.1 (2025-04-14) | SWE-bench Multimodal swe-bench | 31.1% | resolved | 2025-05-31 |
| #8 | Claude 3.7 Sonnet AnthropicZencoder (2025-04-01) | SWE-bench Multimodal swe-bench | 30.6% | resolved | 2025-04-01 |
| #9 | GPT-4o OpenAIGUIRepair + GPT 4o (2024-08-06) | SWE-bench Multimodal swe-bench | 30.4% | resolved | 2025-05-31 |
| #10 | Undisclosed Globant Code Fixer Agent | SWE-bench Multimodal swe-bench | 29.6% | resolved | 2025-03-25 |
| #11 | Undisclosed Zencoder (2025-03-10) | SWE-bench Multimodal swe-bench | 27.1% | resolved | 2025-03-11 |
| #12 | Claude 3.5 Sonnet AnthropicAgentless Lite + Claude-3.5 Sonnet | SWE-bench Multimodal swe-bench | 25.3% | resolved | 2025-02-26 |
| #13 | GPT-4o OpenAISWE-agent Multimodal + GPT 4o (2024-08-06) | SWE-bench Multimodal swe-bench | 12.2% | resolved | 2024-10-06 |
| #14 | Claude Sonnet 3.5 AnthropicSWE-agent + Claude Sonnet 3.5 | SWE-bench Multimodal swe-bench | 12.2% | resolved | 2024-10-06 |
| #15 | Claude Sonnet 3.5 AnthropicSWE-agent JavaScript + Claude Sonnet 3.5 | SWE-bench Multimodal swe-bench | 12% | resolved | 2024-10-06 |
| #16 | GPT-4o OpenAISWE-agent + GPT 4o (2024-08-06) | SWE-bench Multimodal swe-bench | 12% | resolved | 2024-10-06 |
| #17 | Claude 3.5 Sonnet AnthropicSWE-agent Multimodal + Claude 3.5 Sonnet | SWE-bench Multimodal swe-bench | 11.4% | resolved | 2024-10-06 |
| #18 | GPT-4o OpenAISWE-agent JavaScript + GPT 4o (2024-08-06) | SWE-bench Multimodal swe-bench | 9.3% | resolved | 2024-10-06 |
| #19 | Claude 3.5 Sonnet AnthropicAgentless + Claude 3.5 Sonnet | SWE-bench Multimodal swe-bench | 6.2% | resolved | 2024-10-06 |
| #20 | GPT-4o OpenAIRAG + GPT 4o (2024-08-06) | SWE-bench Multimodal swe-bench | 6% | resolved | 2024-10-06 |
| #21 | Claude 3.5 Sonnet AnthropicRAG + Claude 3.5 Sonnet | SWE-bench Multimodal swe-bench | 5% | resolved | 2024-10-06 |
| #22 | GPT-4o OpenAIAgentless + GPT 4o (2024-08-06) | SWE-bench Multimodal swe-bench | 3.1% | resolved | 2024-10-06 |
22 条结果 · 当前 1-22
1 / 1