Google (DeepMind) Gemini 3.8 Flash (no tools)86.2% deepmind.google for Gemini 3.8 Flash (no tools) on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported September 2, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.8 Flash on CharXiv Reasoning — No tools 30004 Google (DeepMind) Gemini 3.7 Flash 84.5% deepmind.google for Gemini 3.7 Flash on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported August 13, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.7 Flash on CharXiv Reasoning — No tools 30010 Meta AI (originally Facebook AI Research) Muse Glimmer 30B (high)78.8% dev.meta.ai for Muse Glimmer 30B (high) on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported August 10, 2026 Model page Meta Self-reported Record for Muse Glimmer 30B on CharXiv Reasoning — No tools 80004 Thinking Machines Lab Inkling-Small (effort=0.99)77.4% thinkingmachines.ai for Inkling-Small (effort=0.99) on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported July 30, 2026 Model card Thinking Machines Lab Self-reported Record for Inkling-Small on CharXiv Reasoning — No tools 160002 Google (DeepMind) Gemini 3.6 Flash 85.2% deepmind.google for Gemini 3.6 Flash on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported July 21, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.6 Flash on CharXiv Reasoning — No tools 30007 Moonshot AI Kimi K3 (max)84.8% huggingface.co for Kimi K3 (max) on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported July 16, 2026 Model card Moonshot AI Self-reported Record for Kimi K3 on CharXiv Reasoning — No tools 120003 Thinking Machines Lab Inkling (effort=0.99)78.1% thinkingmachines.ai for Inkling (effort=0.99) on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported July 15, 2026 Model card Thinking Machines Lab Self-reported Record for Inkling on CharXiv Reasoning — No tools 160001 Meta AI (originally Facebook AI Research) Muse Spark 1.1 (xhigh)88.4% dev.meta.ai for Muse Spark 1.1 (xhigh) on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported July 9, 2026 Model page Meta Self-reported Record for Muse Spark 1.1 on CharXiv Reasoning — No tools 80002 Anthropic Claude Sonnet 5 (max)77.0% www-cdn.anthropic.com for Claude Sonnet 5 (max) on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported June 30, 2026 System card Anthropic Self-reported Record for Claude Sonnet 5 on CharXiv Reasoning — No tools 20013 Google (DeepMind) Gemini 3.5 Flash 84.2% deepmind.google for Gemini 3.5 Flash on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported May 19, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.5 Flash on CharXiv Reasoning — No tools 30006 Moonshot AI Kimi K2.6 (thinking)80.4% huggingface.co for Kimi K2.6 (thinking) on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported April 20, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.6 on CharXiv Reasoning — No tools 120002 Alibaba (Tongyi) Qwen3.6-35B-A3B 78.0% huggingface.co for Qwen3.6-35B-A3B on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported April 17, 2026 Model card Qwen Self-reported Qwen Team Record for Qwen3.6-35B-A3B on CharXiv Reasoning — No tools 130005 Anthropic Claude Opus 4.7 (adaptive thinking, max)82.1% www-cdn.anthropic.com for Claude Opus 4.7 (adaptive thinking, max) on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported April 16, 2026 System card Anthropic Self-reported Record for Claude Opus 4.7 on CharXiv Reasoning — No tools 20010 Meta AI (originally Facebook AI Research) Muse Spark (thinking)86.4% ai.meta.com for Muse Spark (thinking) on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported April 8, 2026 Evaluation methodology Meta Self-reported Record for Muse Spark on CharXiv Reasoning — No tools 80001 Moonshot AI Kimi K2.5 (thinking)77.5% huggingface.co for Kimi K2.5 (thinking) on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported January 27, 2026 Model card Moonshot AI Self-reported Record for Kimi K2.5 on CharXiv Reasoning — No tools 120001 OpenAI GPT-5.2 (xhigh)82.1% openai.com for GPT-5.2 (xhigh) on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on CharXiv Reasoning — No tools 10012