Meta AI (originally Facebook AI Research) Muse Glimmer 30B (high)65.9% dev.meta.ai for Muse Glimmer 30B (high) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported August 10, 2026 Model page Meta Self-reported Record for Muse Glimmer 30B on OSWorld Verified 80004 Alibaba (Tongyi) Qwen3.8-Max 86.1% qwen.ai for Qwen3.8-Max on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported August 3, 2026 Launch post Qwen Team Self-reported Record for Qwen3.8-Max on OSWorld Verified 130008 Google (DeepMind) Gemini 3.6 Flash 83.0% deepmind.google for Gemini 3.6 Flash on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported July 21, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.6 Flash on OSWorld Verified 30007 Moonshot AI Kimi K3 (max)84.8% huggingface.co for Kimi K3 (max) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported July 16, 2026 Model card Moonshot AI Self-reported Record for Kimi K3 on OSWorld Verified 120003 Meta AI (originally Facebook AI Research) Muse Spark 1.1 (xhigh)80.8% dev.meta.ai for Muse Spark 1.1 (xhigh) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported July 9, 2026 Model page Meta Self-reported Record for Muse Spark 1.1 on OSWorld Verified 80002 Anthropic Claude Sonnet 5 (max)81.2% www-cdn.anthropic.com for Claude Sonnet 5 (max) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported June 30, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5 on OSWorld Verified 20013 Anthropic Claude Fable 5 85.0% www-cdn.anthropic.com for Claude Fable 5 on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported June 9, 2026 System card Anthropic Self-reported Record for Claude Fable 5 on OSWorld Verified 20012 Alibaba (Tongyi) Qwen3.6-Plus (enable_thinking=False)62.5% alibabacloud.com for Qwen3.6-Plus (enable_thinking=False) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported June 3, 2026 Launch post Alibaba Cloud Community Self-reported Qwen Team Record for Qwen3.6-Plus on OSWorld Verified 130004 Alibaba (Tongyi) Qwen3.7-Plus (enable_thinking=False)73.3% alibabacloud.com for Qwen3.7-Plus (enable_thinking=False) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported June 3, 2026 Launch post Alibaba Cloud Community Self-reported Qwen Team Record for Qwen3.7-Plus on OSWorld Verified 130007 Anthropic Claude Opus 4.8 (adaptive thinking, max)83.4% www-cdn.anthropic.com for Claude Opus 4.8 (adaptive thinking, max) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported May 28, 2026 System card Anthropic Self-reported Record for Claude Opus 4.8 on OSWorld Verified 20011 Google (DeepMind) Gemini 3.5 Flash 78.4% deepmind.google for Gemini 3.5 Flash on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported May 19, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.5 Flash on OSWorld Verified 30006 OpenAI GPT-5.5 (xhigh)78.7% openai.com for GPT-5.5 (xhigh) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported April 23, 2026 Launch post OpenAI Self-reported Record for GPT-5.5 on OSWorld Verified 10008 Moonshot AI Kimi K2.6 (thinking)73.1% huggingface.co for Kimi K2.6 (thinking) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported April 20, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.6 on OSWorld Verified 120002 OpenAI GPT-5.4 (xhigh)75.0% openai.com for GPT-5.4 (xhigh) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported March 5, 2026 Launch post OpenAI Self-reported Record for GPT-5.4 on OSWorld Verified 10007 Anthropic Claude Sonnet 4.6 (adaptive thinking, max)72.5% www-cdn.anthropic.com for Claude Sonnet 4.6 (adaptive thinking, max) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported February 17, 2026 System card Anthropic Self-reported Record for Claude Sonnet 4.6 on OSWorld Verified 20009 OpenAI GPT-5.3-Codex (xhigh)64.7% openai.com for GPT-5.3-Codex (xhigh) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported February 5, 2026 Launch post OpenAI Self-reported Record for GPT-5.3-Codex on OSWorld Verified 10006 Anthropic Claude Opus 4.6 (adaptive thinking, max)72.7% www-cdn.anthropic.com for Claude Opus 4.6 (adaptive thinking, max) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported February 5, 2026 System card Anthropic Self-reported Record for Claude Opus 4.6 on OSWorld Verified 20008 Anthropic Claude Opus 4.5 (extended thinking)66.3% assets.anthropic.com for Claude Opus 4.5 (extended thinking) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported November 24, 2025 System card Anthropic Self-reported Record for Claude Opus 4.5 on OSWorld Verified 20007