OpenAI GPT-6 Astra (max)64.7% mercor.com for GPT-6 Astra (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-6 Astra on APEX-Agents Original 10005 OpenAI GPT-5.4 (xhigh)52.4% mercor.com for GPT-5.4 (xhigh) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-5.4 on APEX-Agents Original 10007 OpenAI GPT-5.5 (xhigh)55.1% mercor.com for GPT-5.5 (xhigh) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-5.5 on APEX-Agents Original 10008 OpenAI GPT-5.6 Luna (max)43.0% mercor.com for GPT-5.6 Luna (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-5.6 Luna on APEX-Agents Original 10009 OpenAI GPT-5.6 Terra (max)58.2% mercor.com for GPT-5.6 Terra (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-5.6 Terra on APEX-Agents Original 10011 OpenAI GPT-6 Luna (max)44.3% mercor.com for GPT-6 Luna (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-6 Luna on APEX-Agents Original 10013 OpenAI GPT-6 Sol (max)54.3% mercor.com for GPT-6 Sol (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-6 Sol on APEX-Agents Original 10014 OpenAI GPT-6.1 Sol (max)60.0% mercor.com for GPT-6.1 Sol (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-6.1 Sol on APEX-Agents Original 10015 DeepSeek AI DeepSeek-V3.2 21.3% mercor.com for DeepSeek-V3.2 on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for DeepSeek-V3.2 on APEX-Agents Original 110003 Moonshot AI Kimi K3 (max)50.6% mercor.com for Kimi K3 (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Kimi K3 on APEX-Agents Original 120003 Alibaba (Tongyi) Qwen3.5-397B-A17B 24.9% mercor.com for Qwen3.5-397B-A17B on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Qwen3.5-397B-A17B on APEX-Agents Original 130003 Alibaba (Tongyi) Qwen3.8-Max (xhigh)63.3% mercor.com for Qwen3.8-Max (xhigh) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Qwen3.8-Max on APEX-Agents Original 130008 MiniMax MiniMax M3 (high)37.7% mercor.com for MiniMax M3 (high) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for MiniMax M3 on APEX-Agents Original 140003 Z.ai GLM-5.1 40.9% mercor.com for GLM-5.1 on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.1 on APEX-Agents Original 150003 Z.ai GLM-5.2 (max)45.2% mercor.com for GLM-5.2 (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.2 on APEX-Agents Original 150004 Z.ai GLM-5.3 (max)56.6% mercor.com for GLM-5.3 (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.3 on APEX-Agents Original 150005 Z.ai GLM-5.3-Flash (max)52.8% mercor.com for GLM-5.3-Flash (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.3-Flash on APEX-Agents Original 150006 OpenAI gpt-oss-120b (high)4.4% mercor.com for gpt-oss-120b (high) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for gpt-oss-120b on APEX-Agents Original 15001 Thinking Machines Lab Inkling (high)33.8% mercor.com for Inkling (high) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Inkling on APEX-Agents Original 160001 Anthropic Claude Fable 5.1 (high)59.7% mercor.com for Claude Fable 5.1 (high) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Fable 5.1 on APEX-Agents Original 20004 Anthropic Claude Fable 5.1 (max)68.6% mercor.com for Claude Fable 5.1 (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Fable 5.1 on APEX-Agents Original 20004 Anthropic Claude Opus 4.6 (max)46.3% mercor.com for Claude Opus 4.6 (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Opus 4.6 on APEX-Agents Original 20008 Anthropic Claude Sonnet 4.6 (high)43.0% mercor.com for Claude Sonnet 4.6 (high) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 4.6 on APEX-Agents Original 20009 Anthropic Claude Opus 4.7 (max)49.2% mercor.com for Claude Opus 4.7 (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Opus 4.7 on APEX-Agents Original 20010 Anthropic Claude Opus 4.8 (max)48.9% mercor.com for Claude Opus 4.8 (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Opus 4.8 on APEX-Agents Original 20011 Anthropic Claude Fable 5 (max)63.6% mercor.com for Claude Fable 5 (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Fable 5 on APEX-Agents Original 20012 Anthropic Claude Sonnet 5 (max)54.5% mercor.com for Claude Sonnet 5 (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5 on APEX-Agents Original 20013 Anthropic Claude Opus 5 (max)65.8% mercor.com for Claude Opus 5 (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Opus 5 on APEX-Agents Original 20014 Anthropic Claude Opus 5.5 (medium)52.5% mercor.com for Claude Opus 5.5 (medium) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Opus 5.5 on APEX-Agents Original 20015 Anthropic Claude Opus 5.5 (max)73.5% mercor.com for Claude Opus 5.5 (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Opus 5.5 on APEX-Agents Original 20015 Anthropic Claude Sonnet 5.5 (medium)44.6% mercor.com for Claude Sonnet 5.5 (medium) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on APEX-Agents Original 20016 Anthropic Claude Sonnet 5.5 (max)75.5% mercor.com for Claude Sonnet 5.5 (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on APEX-Agents Original 20016 Google (DeepMind) Gemini 3.8 Flash (high)64.3% mercor.com for Gemini 3.8 Flash (high) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.8 Flash on APEX-Agents Original 30004 Google (DeepMind) Gemini 3.1 Pro (high)35.3% mercor.com for Gemini 3.1 Pro (high) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on APEX-Agents Original 30005 Google (DeepMind) Gemini 3.5 Flash (high)27.5% mercor.com for Gemini 3.5 Flash (high) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.5 Flash on APEX-Agents Original 30006 Google (DeepMind) Gemini 3.6 Flash (high)46.9% mercor.com for Gemini 3.6 Flash (high) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.6 Flash on APEX-Agents Original 30007 Google (DeepMind) Gemini 3.7 Flash (high)67.8% mercor.com for Gemini 3.7 Flash (high) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.7 Flash on APEX-Agents Original 30010 Google (DeepMind) Gemini 4 Argon (high)82.4% mercor.com for Gemini 4 Argon (high) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 4 Argon on APEX-Agents Original 30011 SpaceXAI Grok 4.5 (high)56.2% mercor.com for Grok 4.5 (high) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Grok 4.5 on APEX-Agents Original 40001 SpaceXAI Grok 4.6 (xhigh)65.3% mercor.com for Grok 4.6 (xhigh) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Grok 4.6 on APEX-Agents Original 40002 SpaceXAI Grok 4.7 (xhigh)54.6% mercor.com for Grok 4.7 (xhigh) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Grok 4.7 on APEX-Agents Original 40003 NVIDIA NVIDIA Nemotron 3 Ultra 550B-A55B (high)22.7% mercor.com for NVIDIA Nemotron 3 Ultra 550B-A55B (high) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for NVIDIA Nemotron 3 Ultra 550B-A55B on APEX-Agents Original 60003 Meta AI (originally Facebook AI Research) Muse Spark 1.1 (xhigh)31.8% mercor.com for Muse Spark 1.1 (xhigh) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Muse Spark 1.1 on APEX-Agents Original 80002 Meta AI (originally Facebook AI Research) Muse Spark 1.2 (xhigh)36.4% mercor.com for Muse Spark 1.2 (xhigh) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Muse Spark 1.2 on APEX-Agents Original 80003 Meta AI (originally Facebook AI Research) Muse Spark 1.3 (xhigh)58.6% mercor.com for Muse Spark 1.3 (xhigh) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Muse Spark 1.3 on APEX-Agents Original 80005 Meta AI (originally Facebook AI Research) Muse Spark 1.3 (max)47.6% mercor.com for Muse Spark 1.3 (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Muse Spark 1.3 on APEX-Agents Original 80005 MiniMax MiniMax M3 27.7% huggingface.co for MiniMax M3 on APEX-Agents Original (opens in a new tab) Pass rate Reported June 1, 2026 Model card MiniMax Self-reported Record for MiniMax M3 on APEX-Agents Original 140003