Anthropic Claude Haiku 5.5 (max)83.7% anthropic.com for Claude Haiku 5.5 (max) on SWE-bench Multilingual (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 System card Anthropic Self-reported Record for Claude Haiku 5.5 on SWE-bench Multilingual 20018 Anthropic Claude Sonnet 5.5 (max)90.3% anthropic.com for Claude Sonnet 5.5 (max) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on SWE-bench Multilingual 20016 Anthropic Claude Opus 5.5 (max)93.9% www-cdn.anthropic.com for Claude Opus 5.5 (max) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported September 22, 2026 System card Anthropic Self-reported Record for Claude Opus 5.5 on SWE-bench Multilingual 20015 Anthropic Claude Fable 5.1 (max)89.1% www-cdn.anthropic.com for Claude Fable 5.1 (max) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported September 1, 2026 System card Anthropic Self-reported Record for Claude Fable 5.1 on SWE-bench Multilingual 20004 Anthropic Claude Opus 5 (max)89.5% www-cdn.anthropic.com for Claude Opus 5 (max) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported July 24, 2026 System card Anthropic Self-reported Record for Claude Opus 5 on SWE-bench Multilingual 20014 SpaceXAI Grok 4.5 (high)78.0% cursor.com for Grok 4.5 (high) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported July 14, 2026 Model card SpaceXAI and Cursor Self-reported Cursor Record for Grok 4.5 on SWE-bench Multilingual 40001 Anthropic Claude Sonnet 5 (max)78.3% www-cdn.anthropic.com for Claude Sonnet 5 (max) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported June 30, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5 on SWE-bench Multilingual 20013 NVIDIA NVIDIA Nemotron 3 Ultra 550B-A55B 67.7% huggingface.co for NVIDIA Nemotron 3 Ultra 550B-A55B on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported June 4, 2026 Model card NVIDIA Self-reported Record for NVIDIA Nemotron 3 Ultra 550B-A55B on SWE-bench Multilingual 60003 Alibaba (Tongyi) Qwen3.7-Plus 75.8% alibabacloud.com for Qwen3.7-Plus on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported June 3, 2026 Launch post Alibaba Cloud Community Self-reported Qwen Team Record for Qwen3.7-Plus on SWE-bench Multilingual 130007 Anthropic Claude Opus 4.8 (adaptive thinking, max)84.4% www-cdn.anthropic.com for Claude Opus 4.8 (adaptive thinking, max) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported May 28, 2026 System card Anthropic Self-reported Record for Claude Opus 4.8 on SWE-bench Multilingual 20011 Alibaba (Tongyi) Qwen3.7-Max 78.3% alibabacloud.com for Qwen3.7-Max on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported May 21, 2026 Launch post Alibaba Cloud Community Self-reported Qwen Team Record for Qwen3.7-Max on SWE-bench Multilingual 130006 Cursor Composer 2.5 79.8% cursor.com for Composer 2.5 on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported May 18, 2026 Model page Cursor Self-reported Record for Composer 2.5 on SWE-bench Multilingual 50004 DeepSeek AI DeepSeek-V4-Flash (non-thinking)69.7% huggingface.co for DeepSeek-V4-Flash (non-thinking) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported April 24, 2026 Model card DeepSeek Self-reported DeepSeek AI Record for DeepSeek-V4-Flash on SWE-bench Multilingual 110001 DeepSeek AI DeepSeek-V4-Flash (high)70.2% huggingface.co for DeepSeek-V4-Flash (high) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported April 24, 2026 Model card DeepSeek Self-reported DeepSeek AI Record for DeepSeek-V4-Flash on SWE-bench Multilingual 110001 DeepSeek AI DeepSeek-V4-Flash (max)73.3% huggingface.co for DeepSeek-V4-Flash (max) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported April 24, 2026 Model card DeepSeek Self-reported DeepSeek AI Record for DeepSeek-V4-Flash on SWE-bench Multilingual 110001 DeepSeek AI DeepSeek-V4-Pro (max)76.2% huggingface.co for DeepSeek-V4-Pro (max) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported April 24, 2026 Model card DeepSeek Self-reported DeepSeek AI Record for DeepSeek-V4-Pro on SWE-bench Multilingual 110002 DeepSeek AI DeepSeek-V4-Pro (high)74.1% huggingface.co for DeepSeek-V4-Pro (high) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported April 24, 2026 Model card DeepSeek Self-reported DeepSeek AI Record for DeepSeek-V4-Pro on SWE-bench Multilingual 110002 DeepSeek AI DeepSeek-V4-Pro (non-thinking)69.8% huggingface.co for DeepSeek-V4-Pro (non-thinking) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported April 24, 2026 Model card DeepSeek Self-reported DeepSeek AI Record for DeepSeek-V4-Pro on SWE-bench Multilingual 110002 Moonshot AI Kimi K2.6 (thinking)76.7% huggingface.co for Kimi K2.6 (thinking) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported April 20, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.6 on SWE-bench Multilingual 120002 Alibaba (Tongyi) Qwen3.6-35B-A3B 67.2% alibabacloud.com for Qwen3.6-35B-A3B on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported April 17, 2026 Launch post Alibaba Cloud Community Self-reported Qwen Team Record for Qwen3.6-35B-A3B on SWE-bench Multilingual 130005 Anthropic Claude Opus 4.7 (adaptive thinking, max)80.5% www-cdn.anthropic.com for Claude Opus 4.7 (adaptive thinking, max) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported April 16, 2026 System card Anthropic Self-reported Record for Claude Opus 4.7 on SWE-bench Multilingual 20010 Alibaba (Tongyi) Qwen3.6-Plus 73.8% alibabacloud.com for Qwen3.6-Plus on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported April 2, 2026 Launch post Alibaba Cloud Community Self-reported Qwen Team Record for Qwen3.6-Plus on SWE-bench Multilingual 130004 Cursor Composer 1 56.9% cursor.com for Composer 1 on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported March 27, 2026 Technical report Cursor Self-reported Record for Composer 1 on SWE-bench Multilingual 50001 Cursor Composer 1.5 65.9% cursor.com for Composer 1.5 on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported March 27, 2026 Technical report Cursor Self-reported Record for Composer 1.5 on SWE-bench Multilingual 50002 Cursor Composer 2 73.7% cursor.com for Composer 2 on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported March 27, 2026 Technical report Cursor Self-reported Record for Composer 2 on SWE-bench Multilingual 50003 MiniMax MiniMax M2.7 76.5% minimax.io for MiniMax M2.7 on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported March 18, 2026 Launch post MiniMax Self-reported Record for MiniMax M2.7 on SWE-bench Multilingual 140002 NVIDIA NVIDIA Nemotron 3 Super 120B-A12B (OpenHands)45.8% huggingface.co for NVIDIA Nemotron 3 Super 120B-A12B (OpenHands) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported March 11, 2026 Model card NVIDIA Self-reported Record for NVIDIA Nemotron 3 Super 120B-A12B on SWE-bench Multilingual 60002 Alibaba (Tongyi) Qwen3.5-397B-A17B 69.3% alibabacloud.com for Qwen3.5-397B-A17B on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported February 17, 2026 Launch post Alibaba Cloud Community Self-reported Qwen Team Record for Qwen3.5-397B-A17B on SWE-bench Multilingual 130003 Anthropic Claude Sonnet 4.6 (adaptive thinking, max)75.9% www-cdn.anthropic.com for Claude Sonnet 4.6 (adaptive thinking, max) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported February 17, 2026 System card Anthropic Self-reported Record for Claude Sonnet 4.6 on SWE-bench Multilingual 20009 Z.ai GLM-5 (thinking)73.3% z.ai for GLM-5 (thinking) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported February 12, 2026 Launch post Z.ai Self-reported Record for GLM-5 on SWE-bench Multilingual 150002 Anthropic Claude Opus 4.6 (adaptive thinking, max)77.8% www-cdn.anthropic.com for Claude Opus 4.6 (adaptive thinking, max) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported February 5, 2026 System card Anthropic Self-reported Record for Claude Opus 4.6 on SWE-bench Multilingual 20008 Moonshot AI Kimi K2.5 (non-thinking)73.0% huggingface.co for Kimi K2.5 (non-thinking) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported January 27, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.5 on SWE-bench Multilingual 120001 Z.ai GLM-4.7 66.7% z.ai for GLM-4.7 on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported December 22, 2025 Launch post Z.ai Self-reported Record for GLM-4.7 on SWE-bench Multilingual 150001 Mistral AI Devstral 2 61.3% huggingface.co for Devstral 2 on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported December 9, 2025 Model card Mistral AI Self-reported Record for Devstral 2 on SWE-bench Multilingual 90002 Mistral AI Devstral Small 2 55.7% huggingface.co for Devstral Small 2 on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported December 9, 2025 Model card Mistral AI Self-reported Record for Devstral Small 2 on SWE-bench Multilingual 90003