Updated 8 h ago · first seen 11 Sept 2026
bench_01M293SPEGA1XMKH0SMTFTCK2R
- Metric
- resolved · %
- Direction
- Higher is better
- Results
- 180
- Leader
- Claude Opus 4.5 79.2%
Score history · Gemini 2.5 Flash 1 row
Not enough history to chart — a single observation (28.73% on 26 Jul 2025). Rows under different configurations count separately; the list below shows each one.
- 28.73%date=2025-07-26 · board=Verified · system=mini-SWE-agent · model_tag=gemini-2.5-flash26 Jul 2025
Leaderboard 180 current results
Select models with +, then open Compare.
| # | Model | Score | Config | Evaluated | Source | Actions |
|---|---|---|---|---|---|---|
| #101CodeAct v2.1 (claude-3-5-sonnet-20241022)Anthropic | 53% | date=2024-10-29 · board=Verified · system=OpenHands · submission=20241029_OpenHands-CodeAct-2.1-sonnet-20241022 | 29 Oct 2024 | swebench.comT2 | History | |
| #102Claude 3.7 SonnetAnthropic | 52.8% | date=2025-07-20 · board=Verified · system=mini-SWE-agent · model_tag=claude-3-7-sonnet-20250219 | 20 Jul 2025 | swebench.comT2 | History | |
| #103Gemini 2.0 Flash (v20241212-experimental)Google DeepMind | 52.2% | date=2024-12-12 · board=Verified · system=Google Jules · submission=20241212_google_jules_gemini_2.0_flash_experimental | 12 Dec 2024 | swebench.comT2 | History | |
| #104Qwen3 Coder 30B A3B InstructQwen | 52.2% | date=2025-09-01 · board=Verified · system=EntroPO + R2E · model_tag=Qwen3-Coder-30B-A3B-Instruct | 1 Sept 2025 | swebench.comT2 | History | |
| #105claude-35-sonnetAnthropic | 51.8% | date=2024-11-25 · board=Verified · system=Engine Labs · model_tag=claude-3-5-sonnet-20241022 | 25 Nov 2024 | swebench.comT2 | History | |
| #106claude-3-5-sonnet-20241022Anthropic | 51.6% | date=2025-01-22 · board=Verified · system=AutoCodeRover-v2.1 · model_tag=claude-3-5-sonnet-20241022 | 22 Jan 2025 | swebench.comT2 | History | |
| #107Qwen3 Coder 30B A3B InstructQwen | 51.6% | date=2025-08-05 · board=Verified · system=OpenHands · model_tag=https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct | 5 Aug 2025 | swebench.comT2 | History | |
| #108claude-35-sonnetAnthropic | 50.8% | date=2024-12-02 · board=Verified · system=Agentless-1.5 · model_tag=claude-3-5-sonnet-20241022 | 2 Dec 2024 | swebench.comT2 | History | |
| #109Undisclosed | 50% | date=2024-10-28 · board=Verified · system=Solver · submission=20241028_solver | 28 Oct 2024 | swebench.comT2 | History | |
| #110Undisclosed | 50% | date=2024-11-25 · board=Verified · system=Bytedance MarsCode Agent · submission=20241125_marscode-agent-dev | 25 Nov 2024 | swebench.comT2 | History | |
| #111MultipleAnthropic | 49.2% | date=2024-11-05 · board=Verified · system=nFactorial · model_tag=claude-3-5-sonnet-20241022 | 5 Nov 2024 | swebench.comT2 | History | |
| #112claude-35-sonnetAnthropic | 49% | date=2024-10-22 · board=Verified · system=Tools · model_tag=claude-3-5-sonnet-20241022 | 22 Oct 2024 | swebench.comT2 | History | |
| #113MultipleAnthropic | 48.6% | date=2024-10-25 · board=Verified · system=Composio SWE-Kit · model_tag=claude-3-5-sonnet-20241022 | 25 Oct 2024 | swebench.comT2 | History | |
| #114MultipleAnthropic | 47.2% | date=2024-11-06 · board=Verified · system=AppMap Navie v2 · model_tag=claude-3-5-sonnet-20241022 | 6 Nov 2024 | swebench.comT2 | History | |
| #115TTS(Bo8)Qwen | 47% | date=2025-06-16 · board=Verified · system=Skywork-SWE-32B · model_tag=Qwen2.5-Coder-32B-Instruct | 16 Jun 2025 | swebench.comT2 | History | |
| #116Devstral Small 1.0Mistral AI | 46.8% | date=2025-05-20 · board=Verified · system=OpenHands · model_tag=mistralai/Devstral-Small-2505 | 20 May 2025 | swebench.comT2 | History | |
| #117MultipleAnthropic | 46.6% | date=2024-10-23 · board=Verified · system=Emergent E1 · model_tag=claude-3-5-sonnet-20241022 | 23 Oct 2024 | swebench.comT2 | History | |
| #118claude-3-5-sonnet-20241022Anthropic | 46.2% | date=2024-11-08 · board=Verified · system=AutoCodeRover-v2.0 · model_tag=claude-3-5-sonnet-20241022 | 8 Nov 2024 | swebench.comT2 | History | |
| #119Co-PatcheR | 46% | date=2025-05-28 · board=Verified · system=PatchPilot · submission=20250528_patchpilot_Co-PatcheR | 28 May 2025 | swebench.comT2 | History | |
| #120Undisclosed | 45.4% | date=2024-09-24 · board=Verified · system=Solver · submission=20240924_solver | 24 Sept 2024 | swebench.comT2 | History | |
| #121Undisclosed | 45.2% | date=2024-08-24 · board=Verified · system=Gru · submission=20240824_gru | 24 Aug 2024 | swebench.comT2 | History | |
| #122Frogmini 14B 2510 | 45% | date=2025-11-10 · board=Verified · system=FrogMini-14B-2510 · model_tag=FrogMini-14B-2510 | 10 Nov 2025 | swebench.comT2 | History | |
| #123o4-miniOpenAI | 45% | date=2025-07-26 · board=Verified · system=mini-SWE-agent · model_tag=o4-mini-20250416 | 26 Jul 2025 | swebench.comT2 | History | |
| #124gemini-2.0-flash-expGoogle | 44.2% | date=2025-01-18 · board=Verified · system=CodeShellAgent · model_tag=gemini-2.0-flash-exp | 18 Jan 2025 | swebench.comT2 | History | |
| #125Kimi K2 0711Moonshot AI | 43.8% | date=2025-08-07 · board=Verified · system=mini-SWE-agent · model_tag=Kimi-K2-Instruct | 7 Aug 2025 | swebench.comT2 | History | |
| #126Undisclosed | 43.6% | date=2024-09-20 · board=Verified · system=Solver · submission=20240920_solver | 20 Sept 2024 | swebench.comT2 | History | |
| #127Amazon.nova Premier v1:0 | 42.4% | date=2025-05-27 · board=Verified · system=Amazon Nova Premier 1.0 · model_tag=amazon.nova-premier-v1:0 | 27 May 2025 | swebench.comT2 | History | |
| #128o3-miniOpenAI | 42.4% | date=2025-02-14 · board=Verified · system=Agentless Lite · model_tag=o3-mini | 14 Feb 2025 | swebench.comT2 | History | |
| #129DeepSWE-Preview | 42.2% | date=2025-06-29 · board=Verified · system=R2E-Gym · model_tag=https://huggingface.co/agentica-org/DeepSWE-Preview | 29 Jun 2025 | swebench.comT2 | History | |
| #130DeepSeek V3 0324DeepSeek | 42% | date=2025-08-06 · board=Verified · system=SWE-Exp · model_tag=DeepSeek-V3-0324 | 6 Aug 2025 | swebench.comT2 | History | |
| #131MultipleAnthropic | 41.6% | date=2024-10-30 · board=Verified · system=nFactorial · model_tag=claude-3-5-sonnet-20241022 | 30 Oct 2024 | swebench.comT2 | History | |
| #132Undisclosed | 41.6% | date=2025-01-12 · board=Verified · system=ugaiforge · submission=20250112_ugaiforge | 12 Jan 2025 | swebench.comT2 | History | |
| #133Llama3-SWE-RL-70BMeta AI | 41.2% | date=2025-02-26 · board=Verified · system=Agentless Mini · model_tag=Llama3-SWE-RL-70B | 26 Feb 2025 | swebench.comT2 | History | |
| #134claude-35-sonnetAnthropic | 40.6% | date=2024-10-16 · board=Verified · system=Composio SWEkit · model_tag=claude-3-5-sonnet-20241022 | 16 Oct 2024 | swebench.comT2 | History | |
| #135MultipleAnthropic | 40.6% | date=2024-11-13 · board=Verified · system=Nebius AI · model_tag=Llama 3.1 | 13 Nov 2024 | swebench.comT2 | History | |
| #136Claude Haiku 3.5Anthropic | 40.6% | date=2024-10-22 · board=Verified · system=Tools · model_tag=claude-3-haiku-20240307 | 22 Oct 2024 | swebench.comT2 | History | |
| #137Undisclosed | 40.6% | date=2024-08-20 · board=Verified · system=Honeycomb · submission=20240820_honeycomb | 20 Aug 2024 | swebench.comT2 | History | |
| #138SWE-agent-LM-32BQwen | 40.2% | date=2025-05-11 · board=Verified · system=SWE-agent · model_tag=Qwen 2.5 | 11 May 2025 | swebench.comT2 | History | |
| #139claude-35-sonnetAnthropic | 39.6% | date=2024-10-29 · board=Verified · system=EPAM AI/Run Developer Agent · model_tag=claude-3-5-sonnet-20241022 | 29 Oct 2024 | swebench.comT2 | History | |
| #140gpt-4.1OpenAI | 39.58% | date=2025-07-26 · board=Verified · system=mini-SWE-agent · model_tag=gpt-4.1-20250414 | 26 Jul 2025 | swebench.comT2 | History | |
| #141gpt-4oOpenAI | 38.8% | date=2024-10-28 · board=Verified · system=Agentless-1.5 · model_tag=gpt-4o-2024-05-13 | 28 Oct 2024 | swebench.comT2 | History | |
| #142Undisclosed | 38.8% | date=2024-07-21 · board=Verified · system=Amazon Q Developer Agent · submission=20240721_amazon-q-developer-agent-20240719-dev | 21 Jul 2024 | swebench.comT2 | History | |
| #143gpt-4oOpenAI | 38.4% | date=2024-06-28 · board=Verified · system=AutoCodeRover · model_tag=gpt-4o-2024-05-13 | 28 Jun 2024 | swebench.comT2 | History | |
| #144Devstral Small 1.1Mistral AI | 38% | date=2025-07-25 · board=Verified · system=SWE-agent · model_tag=devstral-small-2507 | 25 Jul 2025 | swebench.comT2 | History | |
| #145Qwen2.5 Coder 32B InstructQwen | 38% | date=2025-06-16 · board=Verified · system=Skywork-SWE-32B · model_tag=Qwen2.5-Coder-32B-Instruct | 16 Jun 2025 | swebench.comT2 | History | |
| #146Undisclosed | 37% | date=2024-06-17 · board=Verified · system=Factory Code Droid · submission=20240617_factory_code_droid | 17 Jun 2024 | swebench.comT2 | History | |
| #147gpt-5-nanoOpenAI | 34.8% | date=2025-08-07 · board=Verified · system=mini-SWE-agent · model_tag=gpt-5-nano-2025-08-07 | 7 Aug 2025 | swebench.comT2 | History | |
| #148claude-35-sonnetAnthropic | 33.6% | date=2024-06-20 · board=Verified · system=SWE-agent · model_tag=claude-3-5-sonnet-20241022 | 20 Jun 2024 | swebench.comT2 | History | |
| #149Qwen2.5 (7B + 72B)Qwen | 32.8% | date=2025-03-06 · board=Verified · system=SWE-Fixer · model_tag=Qwen 2.5 | 6 Mar 2025 | swebench.comT2 | History | |
| #150gpt-4oOpenAI | 32.6% | date=2024-06-12 · board=Verified · system=MASAI · model_tag=gpt-4o-2024-08-06 | 12 Jun 2024 | swebench.comT2 | History | |
| #151Undisclosed | 32% | date=2024-11-20 · board=Verified · system=Artemis Agent v1 · submission=20241120_artemis_agent | 20 Nov 2024 | swebench.comT2 | History | |
| #152Undisclosed | 31.6% | date=2024-10-07 · board=Verified · system=nFactorial · submission=20241007_nfactorial | 7 Oct 2024 | swebench.comT2 | History | |
| #153Qwen2.5 (7B + 72B)Qwen | 30.2% | date=2024-11-28 · board=Verified · system=SWE-Fixer · model_tag=Qwen 2.5 | 28 Nov 2024 | swebench.comT2 | History | |
| #154Lingma SWE-GPT 72b (v0925)OpenAI | 28.8% | date=2024-10-02 · board=Verified · system=Lingma Agent · submission=20241002_lingma-agent_lingma-swe-gpt-72b | 2 Oct 2024 | swebench.comT2 | History | |
| #155Gemini 2.5 FlashGoogle | 28.73% | date=2025-07-26 · board=Verified · system=mini-SWE-agent · model_tag=gemini-2.5-flash | 26 Jul 2025 | swebench.comT2 | History | |
| #156gpt-4oOpenAI | 27% | date=2024-10-16 · board=Verified · system=EPAM AI/Run Developer Agent · model_tag=gpt-4o-2024-08-06 | 16 Oct 2024 | swebench.comT2 | History | |
| #157gpt-4oOpenAI | 26.2% | date=2024-06-15 · board=Verified · system=AppMap Navie · model_tag=gpt-4o-2024-05-13 | 15 Jun 2024 | swebench.comT2 | History | |
| #158gpt-oss-120bOpenAI | 26% | date=2025-08-07 · board=Verified · system=mini-SWE-agent · model_tag=gpt-oss-120b | 7 Aug 2025 | swebench.comT2 | History | |
| #159Undisclosed | 25.8% | date=2024-10-01 · board=Verified · system=nFactorial · submission=20241001_nfactorial | 1 Oct 2024 | swebench.comT2 | History | |
| #160Undisclosed | 25.6% | date=2024-05-09 · board=Verified · system=Amazon Q Developer Agent · submission=20240509_amazon-q-developer-agent-20240430-dev | 9 May 2024 | swebench.comT2 | History | |
| #161Lingma SWE-GPT 72b (v0918)OpenAI | 25% | date=2024-09-18 · board=Verified · system=Lingma Agent · submission=20240918_lingma-agent_lingma-swe-gpt-72b | 18 Sept 2024 | swebench.comT2 | History | |
| #162gpt-4oOpenAI | 24% | date=2024-08-20 · board=Verified · system=EPAM AI/Run Developer Agent · model_tag=gpt-4o-2024-08-06 | 20 Aug 2024 | swebench.comT2 | History | |
| #163gpt-4.1-miniOpenAI | 23.94% | date=2025-07-20 · board=Verified · system=mini-SWE-agent · model_tag=gpt-4.1-mini-20250414 | 20 Jul 2025 | swebench.comT2 | History | |
| #164gpt-4oOpenAI | 23.2% | date=2024-07-28 · board=Verified · system=SWE-agent · model_tag=gpt-4o-2024-05-13 | 28 Jul 2024 | swebench.comT2 | History | |
| #165MCTS Refine 7B | 23.2% | date=2025-06-27 · board=Verified · system=MCTS-Refine-7B · model_tag=MCTS-Refine-7B | 27 Jun 2025 | swebench.comT2 | History | |
| #166GPT-4 (1106)OpenAI | 22.4% | date=2024-04-02 · board=Verified · system=SWE-agent · model_tag=gpt-4-1106-preview | 2 Apr 2024 | swebench.comT2 | History | |
| #167gpt-4oOpenAI | 21.62% | date=2025-07-20 · board=Verified · system=mini-SWE-agent · model_tag=gpt-4o-20241120 | 20 Jul 2025 | swebench.comT2 | History | |
| #168Llama 4 Maverick InstructMeta AI | 21.04% | date=2025-07-20 · board=Verified · system=mini-SWE-agent · model_tag=llama-4-maverick-instruct | 20 Jul 2025 | swebench.comT2 | History | |
| #169Lingma SWE-GPT 7b (v0925)OpenAI | 18.2% | date=2024-10-02 · board=Verified · system=Lingma Agent · submission=20241002_lingma-agent_lingma-swe-gpt-7b | 2 Oct 2024 | swebench.comT2 | History | |
| #170claude-3-opusAnthropic | 15.8% | date=2024-04-02 · board=Verified · system=SWE-agent · model_tag=claude-3-opus-20240229 | 2 Apr 2024 | swebench.comT2 | History | |
| #171Gemini 2.0 FlashGoogle | 13.52% | date=2025-07-26 · board=Verified · system=mini-SWE-agent · model_tag=gemini-2.0-flash | 26 Jul 2025 | swebench.comT2 | History | |
| #172Lingma SWE-GPT 7b (v0918)OpenAI | 10.2% | date=2024-09-18 · board=Verified · system=Lingma Agent · submission=20240918_lingma-agent_lingma-swe-gpt-7b | 18 Sept 2024 | swebench.comT2 | History | |
| #173Llama 4 Scout InstructMeta AI | 9.06% | date=2025-07-20 · board=Verified · system=mini-SWE-agent · model_tag=llama-4-scout-instruct | 20 Jul 2025 | swebench.comT2 | History | |
| #174Qwen2.5 Coder 32B InstructQwen | 9% | date=2025-08-03 · board=Verified · system=mini-SWE-agent · model_tag=Qwen2.5-Coder-32B-Instruct | 3 Aug 2025 | swebench.comT2 | History | |
| #175claude-3-opusAnthropic | 7% | date=2024-04-02 · board=Verified · system=RAG baseline · model_tag=claude-3-opus-20240229 | 2 Apr 2024 | swebench.comT2 | History | |
| #176claude-2Anthropic | 4.4% | date=2023-10-10 · board=Verified · system=RAG baseline · model_tag=claude-2 | 10 Oct 2023 | swebench.comT2 | History | |
| #177GPT-4 (1106)OpenAI | 2.8% | date=2024-04-02 · board=Verified · system=RAG baseline · model_tag=gpt-4-1106-preview | 2 Apr 2024 | swebench.comT2 | History | |
| #178SWE-Llama 7BMeta AI | 1.4% | date=2023-10-10 · board=Verified · system=RAG baseline · model_tag=SWE-Llama | 10 Oct 2023 | swebench.comT2 | History | |
| #179SWE-Llama 13BMeta AI | 1.2% | date=2023-10-10 · board=Verified · system=RAG baseline · submission=20231010_rag_swellama13b | 10 Oct 2023 | swebench.comT2 | History | |
| #180GPT-3.5OpenAI | 0.4% | date=2023-10-10 · board=Verified · system=RAG baseline · submission=20231010_rag_gpt35 | 10 Oct 2023 | swebench.comT2 | History |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). The bar is relative to the best score on this page. Results with different configs are not directly comparable — see methodology.
The config filter matches a value inside each result's configuration (server-side, `config=` on the API). Chips are the values shared by several rows on the first page; per-model identifiers are not offered.
Definition
- Category
- coding
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 8 h agomedium
- Task
- resolve real GitHub issues (500 human-validated instances)
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 8 h agomedium
- Metric
- resolved · %
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 8 h agomedium
- Direction
- Higher is better
- Paper
- https://arxiv.org/abs/2310.06770
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 8 h agomedium
- Known limitations
- Scaffold/agent dependent; results are not comparable across harnesses.
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 8 h agomedium
- Website
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 8 h agomedium
Each value shows its source, tier and observation time. Missing rows mean no source stated them. How results are recorded →
- Evaluated models
- Claude Opus 4.6, doubao-seed-code, gemini-3-flash, MiniMax M2.5, Claude Opus 4.5, Gemini 3 Pro Preview, GLM 5, GPT-5.2-Codex +74(82 total)
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history
Categorycategory1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| coding | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Known limitationsknown_limitations1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Scaffold/agent dependent; results are not comparable across harnesses. | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Metricmetric1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| resolved | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Paperpaper1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://arxiv.org/abs/2310.06770 | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Tasktask1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| resolve real GitHub issues (500 human-validated instances) | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Unitunit1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| % | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Websitewebsite1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://www.swebench.com | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| SWE-bench leaderboards | swebench.com/ | leaderboard | T2· Quality secondary | 6 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.