Benchmark
SWE-Bench Pro
SWE-Bench Pro is an advanced version of SWE-Bench that evaluates language models on complex, real-world software engineering tasks requiring extended…
- Modality
- text
- Categories
- reasoning, agents, code
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 50
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Claude Fable 5 | Anthropic | 0.8 | 2026-06-09 | evidence |
| Claude Mythos Preview | Anthropic | 0.778 | 2026-04-07 | evidence |
| Claude Opus 4.7 | Anthropic | 0.643 | 2026-04-16 | evidence |
| Claude Opus 4.8 | Anthropic | 0.692 | 2026-05-28 | evidence |
| Claude Sonnet 5 | Anthropic | 0.632 | 2026-06-30 | evidence |
| DeepSeek-V4-Flash-0423 | DeepSeek | 0.523 | 2026-04-23 | evidence |
| DeepSeek-V4-Flash-Max | DeepSeek | 0.526 | 2026-04-23 | evidence |
| DeepSeek-V4-Pro-Max | DeepSeek | 0.554 | 2026-04-23 | evidence |
| Gemini 3.1 Pro | 0.542 | 2026-02-19 | evidence | |
| Gemini 3.5 Flash | 0.551 | 2026-05-19 | evidence | |
| Gemini 3.5 Flash-Lite | 0.542 | 2026-07-21 | evidence | |
| Gemini 3.6 Flash | 0.587 | 2026-07-21 | evidence | |
| GLM-5.1 | Z.ai | 0.584 | 2026-04-07 | evidence |
| GLM-5.2 | Z.ai | 0.621 | 2026-06-16 | evidence |
| GPT-5.2 Codex | OpenAI | 0.564 | 2026-01-14 | evidence |
| GPT-5.3 Codex | OpenAI | 0.568 | 2026-02-05 | evidence |
| GPT-5.4 | OpenAI | 0.577 | 2026-03-05 | evidence |
| GPT-5.4 mini | OpenAI | 0.544 | 2026-03-17 | evidence |
| GPT-5.4 nano | OpenAI | 0.524 | 2026-03-17 | evidence |
| GPT-5.5 | OpenAI | 0.586 | 2026-04-23 | evidence |
| GPT-5.6 Luna | OpenAI | 0.627 | 2026-07-09 | evidence |
| GPT-5.6 Sol | OpenAI | 0.646 | 2026-07-09 | evidence |
| GPT-5.6 Terra | OpenAI | 0.634 | 2026-07-09 | evidence |
| Grok 4.5 | xAI | 0.647 | 2026-07-16 | evidence |
| Hy3 | Tencent | 0.579 | 2026-07-06 | evidence |
| Inkling-Small | Thinking Machines Lab | 0.559 | 2026-07-30 | evidence |
| Kimi K2.5 | Moonshot AI | 0.507 | 2026-01-27 | evidence |
| Kimi K2.6 | Moonshot AI | 0.586 | 2026-04-20 | evidence |
| Laguna S 2.1 | Poolside | 0.594 | 2026-07-21 | evidence |
| Laguna XS 2.1 | Poolside | 0.476 | 2026-07-02 | evidence |
| MAI-Code-1-Flash | Microsoft | 0.512 | 2026-06-02 | evidence |
| MAI-Thinking-1 | Microsoft | 0.528 | 2026-06-02 | evidence |
| MiMo-V2.5 | Xiaomi | 0.561 | 2026-04-22 | evidence |
| MiMo-V2.5-Pro | Xiaomi | 0.572 | 2026-04-27 | evidence |
| MiniMax M2.5 | MiniMax | 0.554 | 2026-02-12 | evidence |
| MiniMax M2.7 | MiniMax | 0.562 | 2026-03-18 | evidence |
| MiniMax M3 | MiniMax | 0.59 | 2026-06-01 | evidence |
| Muse Glimmer-30B | Meta | 0.512 | 2026-08-10 | evidence |
| Muse Spark | Meta | 0.524 | 2026-04-08 | evidence |
| Muse Spark 1.1 | Meta | 0.615 | 2026-07-09 | evidence |
| North Mini Code 1.0 | Cohere | 0.402 | 2026-06-09 | evidence |
| Qwen3.6 Plus | Qwen | 0.566 | 2026-04-02 | evidence |
| Qwen3.6-27B | Qwen | 0.535 | 2026-04-21 | evidence |
| Qwen3.6-35B-A3B | Qwen | 0.495 | 2026-04-16 | evidence |
| Qwen3.7 Max | Qwen | 0.606 | 2026-05-19 | evidence |
| Qwen3.7-Plus | Qwen | 0.576 | 2026-05-31 | evidence |
| Qwen3.8 Max | Qwen | 0.677 | 2026-08-02 | evidence |
| Qwen3.8-27B | Qwen | 0.617 | 2026-08-14 | evidence |
| Seed 2.1 Pro | ByteDance | 0.575 | 2026-06-24 | evidence |
| Seed 2.1 Turbo | ByteDance | 0.57 | 2026-06-24 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.