OpenAI GPT-4.1 (high)80.5% vals.ai for GPT-4.1 (high) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-4.1 on MMLU-Pro Original — Vals AI harness 10002 OpenAI OpenAI o3 (high)85.6% vals.ai for OpenAI o3 (high) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for OpenAI o3 on MMLU-Pro Original — Vals AI harness 10003 OpenAI OpenAI o4-mini (high)80.6% vals.ai for OpenAI o4-mini (high) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for OpenAI o4-mini on MMLU-Pro Original — Vals AI harness 10004 OpenAI GPT-5.4 (xhigh)87.5% vals.ai for GPT-5.4 (xhigh) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.4 on MMLU-Pro Original — Vals AI harness 10007 OpenAI GPT-5.5 (xhigh)88.1% vals.ai for GPT-5.5 (xhigh) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.5 on MMLU-Pro Original — Vals AI harness 10008 OpenAI GPT-5.6 Luna (max)86.0% vals.ai for GPT-5.6 Luna (max) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.6 Luna on MMLU-Pro Original — Vals AI harness 10009 OpenAI GPT-5.6 Sol (max)89.1% vals.ai for GPT-5.6 Sol (max) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.6 Sol on MMLU-Pro Original — Vals AI harness 10010 OpenAI GPT-5.6 Terra (xhigh)86.7% vals.ai for GPT-5.6 Terra (xhigh) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.6 Terra on MMLU-Pro Original — Vals AI harness 10011 OpenAI GPT-5.2 (xhigh)86.2% vals.ai for GPT-5.2 (xhigh) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.2 on MMLU-Pro Original — Vals AI harness 10012 OpenAI GPT-4.1 mini (high)77.2% vals.ai for GPT-4.1 mini (high) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-4.1 mini on MMLU-Pro Original — Vals AI harness 10016 OpenAI GPT-4.1 nano (high)63.5% vals.ai for GPT-4.1 nano (high) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-4.1 nano on MMLU-Pro Original — Vals AI harness 10017 OpenAI GPT-5 (high)86.5% vals.ai for GPT-5 (high) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5 on MMLU-Pro Original — Vals AI harness 10018 OpenAI GPT-5 mini (high)82.2% vals.ai for GPT-5 mini (high) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5 mini on MMLU-Pro Original — Vals AI harness 10019 OpenAI GPT-5 nano (high)76.1% vals.ai for GPT-5 nano (high) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5 nano on MMLU-Pro Original — Vals AI harness 10020 OpenAI GPT-5.4 mini (xhigh)84.6% vals.ai for GPT-5.4 mini (xhigh) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.4 mini on MMLU-Pro Original — Vals AI harness 10021 OpenAI GPT-5.4 nano (high)77.2% vals.ai for GPT-5.4 nano (high) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.4 nano on MMLU-Pro Original — Vals AI harness 10022 DeepSeek AI DeepSeek-V4-Pro (max)87.2% vals.ai for DeepSeek-V4-Pro (max) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for DeepSeek-V4-Pro on MMLU-Pro Original — Vals AI harness 110002 DeepSeek AI DeepSeek-V3.2 (thinking)84.9% vals.ai for DeepSeek-V3.2 (thinking) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for DeepSeek-V3.2 on MMLU-Pro Original — Vals AI harness 110003 DeepSeek AI DeepSeek-V3.2 83.1% vals.ai for DeepSeek-V3.2 on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for DeepSeek-V3.2 on MMLU-Pro Original — Vals AI harness 110003 Moonshot AI Kimi K2.5 (thinking)85.9% vals.ai for Kimi K2.5 (thinking) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Kimi K2.5 on MMLU-Pro Original — Vals AI harness 120001 Moonshot AI Kimi K2.6 87.6% vals.ai for Kimi K2.6 on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Kimi K2.6 on MMLU-Pro Original — Vals AI harness 120002 Moonshot AI Kimi K3 (max)88.0% vals.ai for Kimi K3 (max) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Kimi K3 on MMLU-Pro Original — Vals AI harness 120003 Alibaba (Tongyi) Qwen3-Max-Thinking 85.0% vals.ai for Qwen3-Max-Thinking on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Qwen3-Max-Thinking on MMLU-Pro Original — Vals AI harness 130002 Alibaba (Tongyi) Qwen3.6-Plus 87.7% vals.ai for Qwen3.6-Plus on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Qwen3.6-Plus on MMLU-Pro Original — Vals AI harness 130004 Alibaba (Tongyi) Qwen3.7-Max 89.3% vals.ai for Qwen3.7-Max on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Qwen3.7-Max on MMLU-Pro Original — Vals AI harness 130006 Alibaba (Tongyi) Qwen3.8-Max 88.6% vals.ai for Qwen3.8-Max on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Qwen3.8-Max on MMLU-Pro Original — Vals AI harness 130008 MiniMax MiniMax M2.5 80.1% vals.ai for MiniMax M2.5 on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for MiniMax M2.5 on MMLU-Pro Original — Vals AI harness 140001 MiniMax MiniMax M2.7 80.4% vals.ai for MiniMax M2.7 on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for MiniMax M2.7 on MMLU-Pro Original — Vals AI harness 140002 MiniMax MiniMax M3 84.2% vals.ai for MiniMax M3 on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for MiniMax M3 on MMLU-Pro Original — Vals AI harness 140003 Z.ai GLM-4.7 82.7% vals.ai for GLM-4.7 on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GLM-4.7 on MMLU-Pro Original — Vals AI harness 150001 Z.ai GLM-5 (thinking)86.0% vals.ai for GLM-5 (thinking) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GLM-5 on MMLU-Pro Original — Vals AI harness 150002 Z.ai GLM-5.1 86.9% vals.ai for GLM-5.1 on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GLM-5.1 on MMLU-Pro Original — Vals AI harness 150003 Z.ai GLM-5.2 86.7% vals.ai for GLM-5.2 on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GLM-5.2 on MMLU-Pro Original — Vals AI harness 150004 Z.ai GLM-5.3 (max)86.8% vals.ai for GLM-5.3 (max) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GLM-5.3 on MMLU-Pro Original — Vals AI harness 150005 Z.ai GLM-5.3-Flash (max)86.1% vals.ai for GLM-5.3-Flash (max) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GLM-5.3-Flash on MMLU-Pro Original — Vals AI harness 150006 Z.ai GLM-4.5 81.2% vals.ai for GLM-4.5 on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GLM-4.5 on MMLU-Pro Original — Vals AI harness 150007 Z.ai GLM-4.6 82.2% vals.ai for GLM-4.6 on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GLM-4.6 on MMLU-Pro Original — Vals AI harness 150009 OpenAI gpt-oss-120b 79.2% vals.ai for gpt-oss-120b on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for gpt-oss-120b on MMLU-Pro Original — Vals AI harness 15001 Thinking Machines Lab Inkling (0.99)86.3% vals.ai for Inkling (0.99) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Inkling on MMLU-Pro Original — Vals AI harness 160001 Thinking Machines Lab Inkling-Small (0.99)85.6% vals.ai for Inkling-Small (0.99) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Inkling-Small on MMLU-Pro Original — Vals AI harness 160002 Anthropic Claude 3.7 Sonnet 80.7% vals.ai for Claude 3.7 Sonnet on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Claude 3.7 Sonnet on MMLU-Pro Original — Vals AI harness 20001 Anthropic Claude 3.7 Sonnet (thinking)82.7% vals.ai for Claude 3.7 Sonnet (thinking) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Claude 3.7 Sonnet on MMLU-Pro Original — Vals AI harness 20001 Anthropic Claude Opus 4 86.2% vals.ai for Claude Opus 4 on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Opus 4 on MMLU-Pro Original — Vals AI harness 20002 Anthropic Claude Sonnet 4 (thinking)83.9% vals.ai for Claude Sonnet 4 (thinking) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Sonnet 4 on MMLU-Pro Original — Vals AI harness 20003 Anthropic Claude Sonnet 4 79.4% vals.ai for Claude Sonnet 4 on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Sonnet 4 on MMLU-Pro Original — Vals AI harness 20003 Anthropic Claude Fable 5.1 92.4% vals.ai for Claude Fable 5.1 on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Fable 5.1 on MMLU-Pro Original — Vals AI harness 20004 Anthropic Claude Sonnet 4.5 (thinking)87.4% vals.ai for Claude Sonnet 4.5 (thinking) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Sonnet 4.5 on MMLU-Pro Original — Vals AI harness 20005 Anthropic Claude Haiku 4.5 (thinking)78.7% vals.ai for Claude Haiku 4.5 (thinking) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Haiku 4.5 on MMLU-Pro Original — Vals AI harness 20006 Anthropic Claude Opus 4.5 85.6% vals.ai for Claude Opus 4.5 on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Opus 4.5 on MMLU-Pro Original — Vals AI harness 20007 Anthropic Claude Opus 4.5 (thinking)87.3% vals.ai for Claude Opus 4.5 (thinking) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Claude Opus 4.5 on MMLU-Pro Original — Vals AI harness 20007