Anthropic Claude Haiku 5.5 (max)64.8% anthropic.com for Claude Haiku 5.5 (max) on SWE-bench Pro Public (opens in a new tab) Archived copy (opens in a new tab) Public tasks resolved Reported October 7, 2026 System card Anthropic Self-reported Record for Claude Haiku 5.5 on SWE-bench Pro Public 20018 Anthropic Claude Sonnet 5.5 (max)81.3% anthropic.com for Claude Sonnet 5.5 (max) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported September 28, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5.5 on SWE-bench Pro Public 20016 Anthropic Claude Opus 5.5 (max)89.9% www-cdn.anthropic.com for Claude Opus 5.5 (max) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported September 22, 2026 System card Anthropic Self-reported Record for Claude Opus 5.5 on SWE-bench Pro Public 20015 Microsoft AI MAI-Thinking-1 52.8% microsoft.ai for MAI-Thinking-1 on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported August 12, 2026 Technical report Microsoft AI Self-reported Microsoft Record for MAI-Thinking-1 on SWE-bench Pro Public 70003 Meta AI (originally Facebook AI Research) Muse Glimmer 30B (high)51.2% dev.meta.ai for Muse Glimmer 30B (high) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported August 10, 2026 Model page Meta Self-reported Record for Muse Glimmer 30B on SWE-bench Pro Public 80004 Thinking Machines Lab Inkling-Small (effort=0.99)55.9% thinkingmachines.ai for Inkling-Small (effort=0.99) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported July 30, 2026 Launch post Thinking Machines Lab Self-reported Record for Inkling-Small on SWE-bench Pro Public 160002 Google (DeepMind) Gemini 3.6 Flash 58.7% deepmind.google for Gemini 3.6 Flash on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported July 21, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.6 Flash on SWE-bench Pro Public 30007 SpaceXAI Grok 4.5 64.7% x.ai for Grok 4.5 on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported July 16, 2026 Launch post SpaceXAI Self-reported Record for Grok 4.5 on SWE-bench Pro Public 40001 Thinking Machines Lab Inkling (effort=0.99)54.3% thinkingmachines.ai for Inkling (effort=0.99) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported July 15, 2026 Launch post Thinking Machines Lab Self-reported Record for Inkling on SWE-bench Pro Public 160001 Meta AI (originally Facebook AI Research) Muse Spark 1.1 (xhigh)61.5% dev.meta.ai for Muse Spark 1.1 (xhigh) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported July 9, 2026 Model page Meta Self-reported Record for Muse Spark 1.1 on SWE-bench Pro Public 80002 Anthropic Claude Sonnet 5 (max)63.2% www-cdn.anthropic.com for Claude Sonnet 5 (max) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported June 30, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5 on SWE-bench Pro Public 20013 Z.ai GLM-5.2 62.1% z.ai for GLM-5.2 on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported June 16, 2026 Launch post Z.ai Self-reported Record for GLM-5.2 on SWE-bench Pro Public 150004 MiniMax MiniMax M3 59.0% minimax.io for MiniMax M3 on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported June 1, 2026 Launch post MiniMax Self-reported Record for MiniMax M3 on SWE-bench Pro Public 140003 Anthropic Claude Opus 4.8 (adaptive thinking, max)69.2% www-cdn.anthropic.com for Claude Opus 4.8 (adaptive thinking, max) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported May 28, 2026 System card Anthropic Self-reported Record for Claude Opus 4.8 on SWE-bench Pro Public 20011 Google (DeepMind) Gemini 3.5 Flash 55.1% deepmind.google for Gemini 3.5 Flash on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported May 19, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.5 Flash on SWE-bench Pro Public 30006 DeepSeek AI DeepSeek-V4-Flash (max)52.6% huggingface.co for DeepSeek-V4-Flash (max) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported April 24, 2026 Model card DeepSeek Self-reported DeepSeek AI Record for DeepSeek-V4-Flash on SWE-bench Pro Public 110001 DeepSeek AI DeepSeek-V4-Pro (max)55.4% huggingface.co for DeepSeek-V4-Pro (max) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported April 24, 2026 Model card DeepSeek Self-reported DeepSeek AI Record for DeepSeek-V4-Pro on SWE-bench Pro Public 110002 Moonshot AI Kimi K2.6 (thinking)58.6% huggingface.co for Kimi K2.6 (thinking) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported April 20, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.6 on SWE-bench Pro Public 120002 Anthropic Claude Opus 4.7 (adaptive thinking, max)64.3% www-cdn.anthropic.com for Claude Opus 4.7 (adaptive thinking, max) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported April 16, 2026 System card Anthropic Self-reported Record for Claude Opus 4.7 on SWE-bench Pro Public 20010 Meta AI (originally Facebook AI Research) Muse Spark (thinking)52.4% ai.meta.com for Muse Spark (thinking) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported April 8, 2026 Evaluation methodology Meta Self-reported Record for Muse Spark on SWE-bench Pro Public 80001 Z.ai GLM-5.1 58.4% z.ai for GLM-5.1 on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported April 7, 2026 Launch post Z.ai Self-reported Record for GLM-5.1 on SWE-bench Pro Public 150003 MiniMax MiniMax M2.7 56.2% minimax.io for MiniMax M2.7 on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported March 18, 2026 Launch post MiniMax Self-reported Record for MiniMax M2.7 on SWE-bench Pro Public 140002 OpenAI GPT-5.4 (xhigh)57.7% openai.com for GPT-5.4 (xhigh) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported March 5, 2026 Launch post OpenAI Self-reported Record for GPT-5.4 on SWE-bench Pro Public 10007 Google (DeepMind) Gemini 3.1 Pro (High)54.2% deepmind.google for Gemini 3.1 Pro (High) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported February 19, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.1 Pro on SWE-bench Pro Public 30005 OpenAI GPT-5.3-Codex (xhigh)56.8% openai.com for GPT-5.3-Codex (xhigh) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported February 5, 2026 Launch post OpenAI Self-reported Record for GPT-5.3-Codex on SWE-bench Pro Public 10006 Moonshot AI Kimi K2.5 (non-thinking)50.7% huggingface.co for Kimi K2.5 (non-thinking) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported January 27, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.5 on SWE-bench Pro Public 120001 OpenAI GPT-5.2 (xhigh)55.6% openai.com for GPT-5.2 (xhigh) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on SWE-bench Pro Public 10012