热度49.9▼ 0.1
SWE-bench Lite
swe-bench / resolved · 84 行结果
| 排名 | 模型 | 子项 | 分数 | Metric | 时间 |
|---|---|---|---|---|---|
| #1 | Claude 4 Sonnet AnthropicExpeRepair-v1.0 + Claude 4 Sonnet | SWE-bench Lite swe-bench | 60.3% | resolved | 2025-06-25 |
| #2 | Multiple AnthropicRefact.ai Agent | SWE-bench Lite swe-bench | 60% | resolved | 2025-04-25 |
| #3 | Claude 4 Sonnet AnthropicKGCompass + Claude 4 Sonnet (20250514) | SWE-bench Lite swe-bench | 58.3% | resolved | 2025-09-06 |
| #4 | Claude 4 Sonnet AnthropicSWE-agent + Claude 4 Sonnet | SWE-bench Lite swe-bench | 56.7% | resolved | 2025-05-26 |
| #5 | Undisclosed Isoform | SWE-bench Lite swe-bench | 55% | resolved | 2025-01-14 |
| #6 | Multiple AnthropicSemAgent_Multi-v1.0 | SWE-bench Lite swe-bench | 51.7% | resolved | 2025-06-25 |
| #7 | Claude 3.5 Sonnet AnthropicIsea | SWE-bench Lite swe-bench | 51.3% | resolved | 2025-09-11 |
| #8 | Qwen3-Coder-30B-A3B-Instruct QwenEntroPO + R2E + Qwen3-Coder-30B-A3B-Instruct | SWE-bench Lite swe-bench | 49.7% | resolved | 2025-09-01 |
| #9 | Undisclosed Blackbox AI Agent | SWE-bench Lite swe-bench | 49% | resolved | 2024-12-20 |
| #10 | Multiple AnthropicCodev | SWE-bench Lite swe-bench | 49% | resolved | 2025-05-28 |
| #11 | Undisclosed Gru(2024-12-08) | SWE-bench Lite swe-bench | 48.7% | resolved | 2024-12-08 |
| #12 | Multiple AnthropicExpeRepair-v1.0 | SWE-bench Lite swe-bench | 48.3% | resolved | 2025-06-13 |
| #13 | Undisclosed Globant Code Fixer Agent | SWE-bench Lite swe-bench | 48.3% | resolved | 2024-11-27 |
| #14 | Claude 3.7 Sonnet AnthropicSWE-agent + Claude 3.7 Sonnet | SWE-bench Lite swe-bench | 48% | resolved | 2025-02-26 |
| #15 | Claude 3.5 Sonnet Anthropicdevlo | SWE-bench Lite swe-bench | 47.3% | resolved | 2024-11-22 |
| #16 | Multiple AnthropicDARS Agent | SWE-bench Lite swe-bench | 47% | resolved | 2025-02-05 |
| #17 | Claude 3.5 Sonnet AnthropicKGCompass + Claude 3.5 Sonnet (20241022) | SWE-bench Lite swe-bench | 46% | resolved | 2025-06-19 |
| #18 | Qwen3-Coder-30B-A3B-Instruct QwenEntroPO + R2E + Qwen3-Coder-30B-A3B-Instruct | SWE-bench Lite swe-bench | 45% | resolved | 2025-09-01 |
| #19 | Claude 3.5 Sonnet AnthropicKodu-v1 + Claude-3.5 Sonnet (20241022) | SWE-bench Lite swe-bench | 44.7% | resolved | 2024-12-07 |
| #20 | Undisclosed CodeFuse-CGM | SWE-bench Lite swe-bench | 44% | resolved | 2025-03-10 |
| #21 | Mixed Models CodeStory Aide + Mixed Models | SWE-bench Lite swe-bench | 43% | resolved | 2024-07-02 |
| #22 | Claude 3.5 Sonnet AnthropicLingxi | SWE-bench Lite swe-bench | 42.7% | resolved | 2025-05-09 |
| #23 | CodeAct v2.1 (claude-3-5-sonnet-20241022) AnthropicOpenHands + CodeAct v2.1 (claude-3-5-sonnet-20241022) | SWE-bench Lite swe-bench | 41.7% | resolved | 2024-10-25 |
| #24 | Multiple AnthropicCodart AI | SWE-bench Lite swe-bench | 41.7% | resolved | 2025-05-15 |
| #25 | Claude 3.5 Sonnet AnthropicPatchKitty-0.9 + Claude-3.5 Sonnet (20241022) | SWE-bench Lite swe-bench | 41.3% | resolved | 2024-12-20 |
84 条结果 · 当前 1-25
1 / 4