Logo

SWE Bench Leaderboard

Compare models on SWE Bench benchmarks.

Last updated: May 22, 2025
RankModelScoreOrganizationLicenseUpdated At
1o3-2025-04-16OpenAI69.1%OpenAIProprietaryMay 22, 2025
2o3OpenAI69.1%OpenAIProprietaryMay 22, 2025
3o4-miniOpenAI68.1%OpenAIProprietaryMay 22, 2025
4google-gemini-2.5-pro-previewGoogle63.8GoogleProprietaryMay 18, 2025
5claude-3-7-sonnet-20250219Anthropic62.3%AnthropicProprietaryMay 22, 2025
6claude-3-7-sonnet-latestAnthropic62.3%AnthropicProprietaryMay 22, 2025
7anthropic-claude-3-7-sonnetAnthropic62.3%AnthropicProprietaryMay 22, 2025
8gpt-4o-miniOpenAI61%OpenAIProprietaryMay 22, 2025
9o3-miniOpenAI61%OpenAIProprietaryMay 22, 2025
10gpt-4.1OpenAI55%OpenAIProprietaryMay 22, 2025
11google-gemini-2.0-flashGoogle51.8GoogleProprietaryMay 18, 2025
12google-gemini-2.0-flash-liveGoogle51.8%GoogleProprietaryMay 18, 2025
13anthropic-claude-3-5-sonnetAnthropic49%AnthropicProprietaryMay 22, 2025
14claude-3-5-sonnet-20241022Anthropic49 %AnthropicProprietaryMay 22, 2025
15claude-3-5-sonnet-20240620Anthropic49%AnthropicProprietaryMay 22, 2025
16claude-3-5-sonnet-latestAnthropic49%AnthropicProprietaryMay 22, 2025
17o1OpenAI48.9%OpenAIProprietaryMay 22, 2025
18claude-3-5-haiku-20241022Anthropic40.6%AnthropicProprietaryMay 22, 2025
19anthropic-claude-3-5-haikuAnthropic40.6%AnthropicProprietaryMay 22, 2025
20claude-3-5-haiku-latestAnthropic40.6%AnthropicProprietaryMay 22, 2025
21gpt-4o-2024-05-13OpenAI31%OpenAIProprietaryMay 22, 2025
22gpt-4o-2024-11-20OpenAI31%OpenAIProprietaryMay 22, 2025
23chatgpt-4oOpenAI31%OpenAIProprietaryMay 22, 2025
24gpt-4oOpenAI31%OpenAIProprietaryMay 22, 2025
25gpt-4o-2024-08-06OpenAI31%OpenAIProprietaryMay 22, 2025
26gpt-4.1-miniOpenAI23.6%OpenAIProprietaryMay 22, 2025