OpenAI GPT-6 Astra (max)63.1% vals.ai for GPT-6 Astra (max) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-6 Astra on Vals Index 2.1 10005 OpenAI GPT-5.6 Luna (max)51.7% vals.ai for GPT-5.6 Luna (max) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.6 Luna on Vals Index 2.1 10009 OpenAI GPT-5.6 Sol (max)58.0% vals.ai for GPT-5.6 Sol (max) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.6 Sol on Vals Index 2.1 10010 OpenAI GPT-5.6 Terra (max)53.1% vals.ai for GPT-5.6 Terra (max) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.6 Terra on Vals Index 2.1 10011 OpenAI GPT-6 Luna (max)51.2% vals.ai for GPT-6 Luna (max) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-6 Luna on Vals Index 2.1 10013 OpenAI GPT-6 Sol (max)57.5% vals.ai for GPT-6 Sol (max) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-6 Sol on Vals Index 2.1 10014 OpenAI GPT-6.1 Sol (max)61.2% vals.ai for GPT-6.1 Sol (max) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-6.1 Sol on Vals Index 2.1 10015 OpenAI GPT-5.4 mini (xhigh)33.2% vals.ai for GPT-5.4 mini (xhigh) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.4 mini on Vals Index 2.1 10021 DeepSeek AI DeepSeek-V4-Pro (max)38.6% vals.ai for DeepSeek-V4-Pro (max) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for DeepSeek-V4-Pro on Vals Index 2.1 110002 Moonshot AI Kimi K3 (max)50.3% vals.ai for Kimi K3 (max) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Kimi K3 on Vals Index 2.1 120003 Alibaba (Tongyi) Qwen3.8-Max 48.3% vals.ai for Qwen3.8-Max on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Qwen3.8-Max on Vals Index 2.1 130008 MiniMax MiniMax M3 36.5% vals.ai for MiniMax M3 on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for MiniMax M3 on Vals Index 2.1 140003 Z.ai GLM-5.3 (max)53.5% vals.ai for GLM-5.3 (max) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for GLM-5.3 on Vals Index 2.1 150005 Thinking Machines Lab Inkling (0.99)28.7% vals.ai for Inkling (0.99) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Inkling on Vals Index 2.1 160001 Thinking Machines Lab Inkling-Small (0.99)25.5% vals.ai for Inkling-Small (0.99) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Inkling-Small on Vals Index 2.1 160002 Anthropic Claude Opus 4.8 55.1% vals.ai for Claude Opus 4.8 on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Opus 4.8 on Vals Index 2.1 20011 Anthropic Claude Fable 5 61.4% vals.ai for Claude Fable 5 on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Fable 5 on Vals Index 2.1 20012 Anthropic Claude Sonnet 5 51.8% vals.ai for Claude Sonnet 5 on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Sonnet 5 on Vals Index 2.1 20013 Anthropic Claude Opus 5 63.7% vals.ai for Claude Opus 5 on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Opus 5 on Vals Index 2.1 20014 Google (DeepMind) Gemini 3.8 Flash (high)54.8% vals.ai for Gemini 3.8 Flash (high) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Gemini 3.8 Flash on Vals Index 2.1 30004 Google (DeepMind) Gemini 3.1 Pro (high)33.4% vals.ai for Gemini 3.1 Pro (high) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Gemini 3.1 Pro on Vals Index 2.1 30005 Google (DeepMind) Gemini 3.5 Flash (high)44.8% vals.ai for Gemini 3.5 Flash (high) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Gemini 3.5 Flash on Vals Index 2.1 30006 Google (DeepMind) Gemini 3.7 Flash (high)51.3% vals.ai for Gemini 3.7 Flash (high) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Gemini 3.7 Flash on Vals Index 2.1 30010 SpaceXAI Grok 4.5 (high)44.7% vals.ai for Grok 4.5 (high) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Grok 4.5 on Vals Index 2.1 40001 SpaceXAI Grok 4.6 (high)52.1% vals.ai for Grok 4.6 (high) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Grok 4.6 on Vals Index 2.1 40002 SpaceXAI Grok 4.7 (xhigh)54.9% vals.ai for Grok 4.7 (xhigh) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Grok 4.7 on Vals Index 2.1 40003 Meta AI (originally Facebook AI Research) Muse Spark 1.2 (xhigh)49.3% vals.ai for Muse Spark 1.2 (xhigh) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Muse Spark 1.2 on Vals Index 2.1 80003 Meta AI (originally Facebook AI Research) Muse Spark 1.3 (xhigh)53.2% vals.ai for Muse Spark 1.3 (xhigh) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Muse Spark 1.3 on Vals Index 2.1 80005 Google (DeepMind) Gemini 4 Argon (high)68.9% deepmind.google for Gemini 4 Argon (high) on Vals Index 2.1 (opens in a new tab) Vals Index GDP-weighted Accuracy Reported September 30, 2026 Evaluation methodology Google DeepMind Self-reported Vals AI Record for Gemini 4 Argon on Vals Index 2.1 30011