# SWE-bench Verified leaderboard

Coding benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/coding-swe-verified

Software Engineering Benchmark Verified. Every model the catalog carries a published SWE-bench Verified value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Coding |
| Measure | Code patch generation |
| Tasks | 500 verified issues |
| Difficulty | Professional software engineering |
| Published by | [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://arxiv.org/abs/2310.06770) |

SWE-bench Verified tests patches for 500 human-filtered GitHub issues. A score measures how many tasks an evaluated model-and-agent setup resolved; the model name alone does not identify that setup.

## SWE-bench Verified ranking

117 models with a published SWE-bench Verified value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Code patch generation | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Opus 5](https://modelscale.dev/models/claude-opus-5) | Anthropic | 96 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Mythos 5](https://modelscale.dev/models/claude-mythos-5) | Anthropic | 95.5 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Fable 5](https://modelscale.dev/models/claude-fable-5) | Anthropic | 95 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Ember-1](https://modelscale.dev/models/ember-1) | Fireworks | 92.2 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Claude Opus 4.8](https://modelscale.dev/models/claude-opus-4-8) | Anthropic | 88.6 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Claude Opus 4.7](https://modelscale.dev/models/claude-opus-4-7) | Anthropic | 87.6 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Claude Opus 4.7 (Adaptive)](https://modelscale.dev/models/claude-opus-4-7-max) | Anthropic | 87.6 | Last good 2026-11-18 · source benchlm:models |
| 8 | [Ornith-1.5-397B](https://modelscale.dev/models/ornith-1-5-397b) | Ornith AI | 86 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Claude Sonnet 5](https://modelscale.dev/models/claude-sonnet-5) | Anthropic | 85.2 | Observed 2026-11-21 · source benchlm:models |
| 10 | [GPT-5.3 Codex](https://modelscale.dev/models/gpt-5-3-codex) | OpenAI | 85 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Ornith-1.0-397B](https://modelscale.dev/models/ornith-1-0-397b) | DeepReinforce AI | 82.4 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Inkling 2 Small](https://modelscale.dev/models/inkling-2-small) | Thinking Machines Lab | 82.2 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Beam 1.0 501B-A23B](https://modelscale.dev/models/reflection-beam) | Reflection AI | 81.6 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Claude Opus 4.5](https://modelscale.dev/models/claude-opus-4-5) | Anthropic | 80.9 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Claude Opus 4.6](https://modelscale.dev/models/claude-opus-4-6) | Anthropic | 80.84 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Beam 1.0 501B-A23B NVFP4](https://modelscale.dev/models/reflection-beam-nvfp4) | Reflection AI | 80.7 | Observed 2026-11-21 · source benchlm:models |
| 17 | [DeepSeek V4 Pro](https://modelscale.dev/models/deepseek-v4-pro) | DeepSeek | 80.6 | Observed 2026-11-21 · source benchlm:models |
| 17 | [DeepSeek V4 Pro 0813](https://modelscale.dev/models/deepseek-v4-pro-max) | DeepSeek | 80.6 | Last good 2026-11-18 · source benchlm:models |
| 19 | [MiniMax M3](https://modelscale.dev/models/minimax-m3) | MiniMax | 80.5 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Qwen3.7 Max](https://modelscale.dev/models/qwen3-7-max) | Alibaba | 80.4 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Beam 1.0 501B-A23B FP8](https://modelscale.dev/models/reflection-beam-fp8) | Reflection AI | 80.2 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Inkling-Small](https://modelscale.dev/models/inkling-small) | Thinking Machines Lab | 80.2 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Kimi K2.6](https://modelscale.dev/models/kimi-2-6) | Moonshot AI | 80.2 | Observed 2026-11-21 · source benchlm:models |
| 24 | [GPT-5.2](https://modelscale.dev/models/gpt-5-2) | OpenAI | 80 | Observed 2026-11-21 · source benchlm:models |
| 25 | [Claude Sonnet 4.6](https://modelscale.dev/models/claude-sonnet-4-6) | Anthropic | 79.6 | Observed 2026-11-21 · source benchlm:models |
| 26 | [Inkling 2 Mini](https://modelscale.dev/models/inkling-2-mini) | Thinking Machines Lab | 79.2 | Observed 2026-11-21 · source benchlm:models |
| 27 | [DeepSeek V4 Flash 0731](https://modelscale.dev/models/deepseek-v4-flash-max) | DeepSeek | 79 | Observed 2026-11-21 · source benchlm:models |
| 27 | [Ornith-1.5-35B-A3B](https://modelscale.dev/models/ornith-1-5-35b-a3b) | Ornith AI | 79 | Observed 2026-11-21 · source benchlm:models |
| 29 | [Qwen3.6 Plus](https://modelscale.dev/models/qwen3-6-plus) | Alibaba | 78.8 | Observed 2026-11-21 · source benchlm:models |
| 30 | [BTL-4](https://modelscale.dev/models/btl-4) | Bad Theory Labs | 78.4 | Observed 2026-11-21 · source benchlm:models |
| 30 | [dots3-note Preview](https://modelscale.dev/models/dots3-note-preview) | Dots Studio | 78.4 | Observed 2026-11-21 · source benchlm:models |
| 32 | [MiMo-V2-Pro](https://modelscale.dev/models/mimo-v2-pro) | Xiaomi | 78 | Observed 2026-11-21 · source benchlm:models |
| 33 | [GLM-5](https://modelscale.dev/models/glm-5) | Z.AI | 77.8 | Observed 2026-11-21 · source benchlm:models |
| 34 | [Apodex 1.1](https://modelscale.dev/models/apodex-1-1) | Apodex | 77.7 | Observed 2026-11-21 · source benchlm:models |
| 34 | [Qwen3.7 Plus](https://modelscale.dev/models/qwen3-7-plus) | Alibaba | 77.7 | Observed 2026-11-21 · source benchlm:models |
| 36 | [Inkling](https://modelscale.dev/models/inkling) | Thinking Machines Lab | 77.6 | Observed 2026-11-21 · source benchlm:models |
| 36 | [Mistral Medium 3.5 128B](https://modelscale.dev/models/mistral-medium-3-5-128b) | Mistral | 77.6 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Muse Spark](https://modelscale.dev/models/muse-spark) | Meta | 77.4 | Observed 2026-11-21 · source benchlm:models |
| 39 | [Claude Sonnet 4.5](https://modelscale.dev/models/claude-sonnet-4-5) | Anthropic | 77.2 | Observed 2026-11-21 · source benchlm:models |
| 39 | [Qwen3.6-27B](https://modelscale.dev/models/qwen3-6-27b) | Alibaba | 77.2 | Observed 2026-11-21 · source benchlm:models |
| 41 | [Kimi K2.5](https://modelscale.dev/models/kimi-k2-5) | Moonshot AI | 76.8 | Observed 2026-11-21 · source benchlm:models |
| 41 | [Kimi K2.5 (Reasoning)](https://modelscale.dev/models/kimi-k2-5-reasoning) | Moonshot AI | 76.8 | Last good 2026-11-18 · source benchlm:models |
| 43 | [Grok 4.20](https://modelscale.dev/models/grok-4-20-beta) | xAI | 76.7 | Observed 2026-11-21 · source benchlm:models |
| 44 | [Ripple-65B Preview](https://modelscale.dev/models/ripple-65b-preview) | Ricursive Intelligence | 76.5 | Observed 2026-11-21 · source benchlm:models |
| 45 | [Qwen3.5 397B](https://modelscale.dev/models/qwen3-5-397b) | Alibaba | 76.2 | Observed 2026-11-21 · source benchlm:models |
| 46 | [Muse Glimmer 30B](https://modelscale.dev/models/muse-glimmer-30b) | Meta | 76 | Observed 2026-11-21 · source benchlm:models |
| 47 | [Ornith-1.0-35B](https://modelscale.dev/models/ornith-1-0-35b) | DeepReinforce AI | 75.6 | Observed 2026-11-21 · source benchlm:models |
| 48 | [MiMo-V2-Omni](https://modelscale.dev/models/mimo-v2-omni) | Xiaomi | 74.8 | Observed 2026-11-21 · source benchlm:models |
| 49 | [Laguna M.1](https://modelscale.dev/models/laguna-m-1) | Poolside | 74.6 | Observed 2026-11-21 · source benchlm:models |
| 50 | [Claude 4.1 Opus](https://modelscale.dev/models/claude-4-1-opus) | Anthropic | 74.5 | Observed 2026-11-21 · source benchlm:models |
| 51 | [Hy3 Preview](https://modelscale.dev/models/hy3-preview) | Tencent | 74.4 | Observed 2026-11-21 · source benchlm:models |
| 51 | [Step 3.5 Flash](https://modelscale.dev/models/step-3-5-flash) | StepFun | 74.4 | Observed 2026-11-21 · source benchlm:models |
| 53 | [Flint](https://modelscale.dev/models/flint-40b-a2-5b) | Recursive | 74.2 | Observed 2026-11-21 · source benchlm:models |
| 54 | [GLM-4.7](https://modelscale.dev/models/glm-4-7) | Z.AI | 73.8 | Observed 2026-11-21 · source benchlm:models |
| 55 | [MAI-Thinking-1](https://modelscale.dev/models/mai-thinking-1) | Microsoft | 73.5 | Observed 2026-11-21 · source benchlm:models |
| 56 | [MiMo-V2-Flash](https://modelscale.dev/models/mimo-v2-flash) | Xiaomi | 73.4 | Observed 2026-11-21 · source benchlm:models |
| 56 | [Qwen3.6-35B-A3B](https://modelscale.dev/models/qwen3-6-35b-a3b) | Alibaba | 73.4 | Observed 2026-11-21 · source benchlm:models |
| 58 | [Claude Haiku 4.5](https://modelscale.dev/models/claude-haiku-4-5) | Anthropic | 73.3 | Observed 2026-11-21 · source benchlm:models |
| 59 | [Jais-3-MoVA-36B-A4B](https://modelscale.dev/models/jais-3-mova-36b-a4b) | IFM | 72.8 | Observed 2026-11-21 · source benchlm:models |
| 60 | [Claude 4 Sonnet](https://modelscale.dev/models/claude-4-sonnet) | Anthropic | 72.7 | Observed 2026-11-21 · source benchlm:models |
| 61 | [MAI-Code-1.1-Flash](https://modelscale.dev/models/mai-code-1-1-flash) | Microsoft | 72.6 | Observed 2026-11-21 · source benchlm:models |
| 62 | [Claude 4 Opus](https://modelscale.dev/models/claude-4-opus) | Anthropic | 72.5 | Observed 2026-11-21 · source benchlm:models |
| 63 | [Jais-3-32B](https://modelscale.dev/models/jais-3-32b) | IFM | 72.4 | Observed 2026-11-21 · source benchlm:models |
| 63 | [Qwen3.5-27B](https://modelscale.dev/models/qwen3-5-27b) | Alibaba | 72.4 | Observed 2026-11-21 · source benchlm:models |
| 65 | [Qwen3.5-122B-A10B](https://modelscale.dev/models/qwen3-5-122b-a10b) | Alibaba | 72 | Observed 2026-11-21 · source benchlm:models |
| 66 | [Nemotron 3 Ultra](https://modelscale.dev/models/nemotron-3-ultra-500b) | NVIDIA | 71.9 | Observed 2026-11-21 · source benchlm:models |
| 67 | [Nemotron 3.5 Super VL 120B A12B](https://modelscale.dev/models/nemotron-3-5-super-vl-120b-a12b) | NVIDIA | 71.1 | Observed 2026-11-21 · source benchlm:models |
| 68 | [Nemotron 3.5 Super VL 120B A12B NVFP4](https://modelscale.dev/models/nemotron-3-5-super-vl-120b-a12b-nvfp4) | NVIDIA | 71.07 | Observed 2026-11-21 · source benchlm:models |
| 69 | [Laguna XS 2.1](https://modelscale.dev/models/laguna-xs-2-1) | Poolside | 70.9 | Observed 2026-11-21 · source benchlm:models |
| 70 | [Grok Code Fast 1](https://modelscale.dev/models/grok-code-fast-1) | xAI | 70.8 | Observed 2026-11-21 · source benchlm:models |
| 71 | [Ornith-1.5-9B](https://modelscale.dev/models/ornith-1-5-9b) | Ornith AI | 70.6 | Observed 2026-11-21 · source benchlm:models |
| 71 | [Solar Pro 4](https://modelscale.dev/models/solar-pro-4) | Upstage | 70.6 | Observed 2026-11-21 · source benchlm:models |
| 73 | [Solar Open 2](https://modelscale.dev/models/solar-open-2) | Upstage | 70.4 | Observed 2026-11-21 · source benchlm:models |
| 74 | [Jais-3-375B-A23B](https://modelscale.dev/models/jais-3-375b-a23b) | IFM | 70.2 | Observed 2026-11-21 · source benchlm:models |
| 74 | [Jais-3-7B](https://modelscale.dev/models/jais-3-7b) | IFM | 70.2 | Observed 2026-11-21 · source benchlm:models |
| 76 | [Laguna XS.2](https://modelscale.dev/models/laguna-xs-2) | Poolside | 69.9 | Observed 2026-11-21 · source benchlm:models |
| 77 | [Qwen3-Coder 480B-A35B](https://modelscale.dev/models/qwen3-coder-480b-a35b) | Alibaba | 69.6 | Observed 2026-11-21 · source benchlm:models |
| 78 | [Ornith-1.0-9B](https://modelscale.dev/models/ornith-1-0-9b) | DeepReinforce AI | 69.4 | Observed 2026-11-21 · source benchlm:models |
| 79 | [Qwen3.5-35B-A3B](https://modelscale.dev/models/qwen3-5-35b-a3b) | Alibaba | 69.2 | Observed 2026-11-21 · source benchlm:models |
| 80 | [K-EXAONE 2.0](https://modelscale.dev/models/k-exaone-2-0) | LG AI Research | 68.2 | Observed 2026-11-21 · source benchlm:models |
| 80 | [LongCat-Flash-Lite-Sparse](https://modelscale.dev/models/longcat-flash-lite-sparse) | Meituan | 68.2 | Observed 2026-11-21 · source benchlm:models |
| 82 | [DeepSeek V3.1](https://modelscale.dev/models/deepseek-v3-1) | DeepSeek | 66 | Observed 2026-11-21 · source benchlm:models |
| 83 | [Kimi K2](https://modelscale.dev/models/kimi-k2) | Moonshot AI | 65.8 | Observed 2026-11-21 · source benchlm:models |
| 84 | [Gemini 2.5 Pro](https://modelscale.dev/models/gemini-2-5-pro) | Google | 63.8 | Observed 2026-11-21 · source benchlm:models |
| 85 | [Spark-X2.6-4B](https://modelscale.dev/models/spark-x2-6-4b) | SparkLLM | 62.8 | Observed 2026-11-21 · source benchlm:models |
| 86 | [GPT-OSS 120B](https://modelscale.dev/models/gpt-oss-120b) | OpenAI | 62.4 | Observed 2026-11-21 · source benchlm:models |
| 87 | [Claude 3.7 Sonnet](https://modelscale.dev/models/claude-3-7-sonnet) | Anthropic | 62.3 | Observed 2026-11-21 · source benchlm:models |
| 88 | [Ternary Bonsai 2 27B](https://modelscale.dev/models/ternary-bonsai-2-27b) | Prism ML | 60.8 | Observed 2026-11-21 · source benchlm:models |
| 89 | [GPT-OSS 20B](https://modelscale.dev/models/gpt-oss-20b) | OpenAI | 60.7 | Observed 2026-11-21 · source benchlm:models |
| 90 | [Nemotron 3 Super 100B](https://modelscale.dev/models/nemotron-3-super-100b) | NVIDIA | 60.47 | Observed 2026-11-21 · source benchlm:models |
| 91 | [GLM-4.7-Flash](https://modelscale.dev/models/glm-4-7-flash) | Z.AI | 59.2 | Observed 2026-11-21 · source benchlm:models |
| 92 | [DeepSeek-R1-0528](https://modelscale.dev/models/deepseek-r1-0528) | DeepSeek | 57.6 | Observed 2026-11-21 · source benchlm:models |
| 93 | [Granite 4.2 30B](https://modelscale.dev/models/granite-4-2-30b) | IBM | 57 | Observed 2026-11-21 · source benchlm:models |
| 94 | [MiniMax M1 80k](https://modelscale.dev/models/minimax-m1-80k) | MiniMax | 56 | Observed 2026-11-21 · source benchlm:models |
| 95 | [GPT-4.1](https://modelscale.dev/models/gpt-4-1) | OpenAI | 54.6 | Observed 2026-11-21 · source benchlm:models |
| 96 | [ZAYA1-74B-Preview](https://modelscale.dev/models/zaya1-74b-preview) | Zyphra | 53.2 | Observed 2026-11-21 · source benchlm:models |
| 97 | [Nemotron 3.5 Lightning 30B A3B NVFP4](https://modelscale.dev/models/nemotron-3-5-lightning-30b-a3b-nvfp4) | NVIDIA | 52.8 | Observed 2026-11-21 · source benchlm:models |
| 98 | [LFM2.5-24B-A2B](https://modelscale.dev/models/lfm2-5-24b-a2b) | LiquidAI | 51 | Observed 2026-11-21 · source benchlm:models |
| 99 | [K-Exaone](https://modelscale.dev/models/k-exaone) | LG AI Research | 49.4 | Observed 2026-11-21 · source benchlm:models |
| 100 | [o3-mini](https://modelscale.dev/models/o3-mini) | OpenAI | 49.3 | Observed 2026-11-21 · source benchlm:models |
| 101 | [LLaDA2.2-flash](https://modelscale.dev/models/llada2-2-flash) | InclusionAI | 49.28 | Observed 2026-11-21 · source benchlm:models |
| 102 | [DeepSeek-R1](https://modelscale.dev/models/deepseek-r1) | DeepSeek | 49.2 | Observed 2026-11-21 · source benchlm:models |
| 103 | [Claude 3.5 Sonnet](https://modelscale.dev/models/claude-3-5-sonnet) | Anthropic | 49 | Observed 2026-11-21 · source benchlm:models |
| 104 | [Granite 4.2 8B](https://modelscale.dev/models/granite-4-2-8b) | IBM | 47.67 | Observed 2026-11-21 · source benchlm:models |
| 105 | [Mellum2.1-12B-A2.5B-Thinking](https://modelscale.dev/models/mellum2-1-12b-a2-5b-thinking) | JetBrains | 47 | Observed 2026-11-21 · source benchlm:models |
| 106 | [Devstral Small](https://modelscale.dev/models/devstral-small) | Mistral | 46.8 | Observed 2026-11-21 · source benchlm:models |
| 107 | [MiniCPM5-2B](https://modelscale.dev/models/minicpm5-2b) | OpenBMB | 46.4 | Observed 2026-11-21 · source benchlm:models |
| 108 | [Sarvam 105B](https://modelscale.dev/models/sarvam-105b) | Sarvam | 45 | Observed 2026-11-21 · source benchlm:models |
| 109 | [LFM3-1.7B](https://modelscale.dev/models/lfm3-1-7b) | LiquidAI | 43.4 | Observed 2026-11-21 · source benchlm:models |
| 110 | [DeepSeek V3](https://modelscale.dev/models/deepseek-v3) | DeepSeek | 42 | Observed 2026-11-21 · source benchlm:models |
| 111 | [Claude 3.5 Haiku](https://modelscale.dev/models/claude-3-5-haiku) | Anthropic | 40.6 | Observed 2026-11-21 · source benchlm:models |
| 112 | [Sarvam 30B](https://modelscale.dev/models/sarvam-30b) | Sarvam | 34 | Observed 2026-11-21 · source benchlm:models |
| 113 | [Gemini 2.5 Flash-Lite](https://modelscale.dev/models/gemini-2-5-flash-lite) | Google | 31.6 | Observed 2026-11-21 · source benchlm:models |
| 114 | [GPT-4.1 mini](https://modelscale.dev/models/gpt-4-1-mini) | OpenAI | 23.6 | Observed 2026-11-21 · source benchlm:models |
| 115 | [Gemini 2.0 Flash](https://modelscale.dev/models/gemini-2-0-flash) | Google | 21.4 | Observed 2026-11-21 · source benchlm:models |
| 116 | [Gemini 2.0 Flash-Lite](https://modelscale.dev/models/gemini-2-0-flash-lite) | Google | 12.5 | Observed 2026-11-21 · source benchlm:models |
| 117 | [Gemini 1.5 Flash](https://modelscale.dev/models/gemini-1-5-flash) | Google | 9.6 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
