OpenAI GPT-6 Astra (xhigh)48.9% mercor.com for GPT-6 Astra (xhigh) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-6 Astra on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 10005 OpenAI GPT-6 Astra (max)47.8% mercor.com for GPT-6 Astra (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-6 Astra on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 10005 OpenAI GPT-5.4 (xhigh)37.1% mercor.com for GPT-5.4 (xhigh) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-5.4 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 10007 OpenAI GPT-5.5 (xhigh)45.2% mercor.com for GPT-5.5 (xhigh) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-5.5 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 10008 OpenAI GPT-5.6 Luna (max)46.0% mercor.com for GPT-5.6 Luna (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-5.6 Luna on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 10009 OpenAI GPT-5.6 Terra (max)45.2% mercor.com for GPT-5.6 Terra (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-5.6 Terra on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 10011 OpenAI GPT-6 Luna (max)33.9% mercor.com for GPT-6 Luna (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-6 Luna on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 10013 OpenAI GPT-6 Sol (max)44.1% mercor.com for GPT-6 Sol (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-6 Sol on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 10014 OpenAI GPT-6.1 Sol (max)48.4% mercor.com for GPT-6.1 Sol (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-6.1 Sol on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 10015 DeepSeek AI DeepSeek-V4-Pro (max)25.0% mercor.com for DeepSeek-V4-Pro (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for DeepSeek-V4-Pro on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 110002 DeepSeek AI DeepSeek-V3.2 5.9% mercor.com for DeepSeek-V3.2 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for DeepSeek-V3.2 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 110003 Moonshot AI Kimi K3 (max)52.7% mercor.com for Kimi K3 (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Kimi K3 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 120003 Alibaba (Tongyi) Qwen3.8-Max (xhigh)50.5% mercor.com for Qwen3.8-Max (xhigh) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Qwen3.8-Max on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 130008 MiniMax MiniMax M3 (high)37.9% mercor.com for MiniMax M3 (high) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for MiniMax M3 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 140003 Z.ai GLM-5.2 (max)46.0% mercor.com for GLM-5.2 (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.2 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 150004 Z.ai GLM-5.3 (max)42.5% mercor.com for GLM-5.3 (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.3 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 150005 Thinking Machines Lab Inkling (high)21.2% mercor.com for Inkling (high) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Inkling on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 160001 Anthropic Claude Fable 5.1 (max)43.3% mercor.com for Claude Fable 5.1 (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Fable 5.1 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 20004 Anthropic Claude Fable 5.1 (high)42.7% mercor.com for Claude Fable 5.1 (high) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Fable 5.1 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 20004 Anthropic Claude Sonnet 4.6 (high)35.5% mercor.com for Claude Sonnet 4.6 (high) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 4.6 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 20009 Anthropic Claude Opus 4.7 (max)47.0% mercor.com for Claude Opus 4.7 (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Opus 4.7 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 20010 Anthropic Claude Opus 4.8 (max)44.4% mercor.com for Claude Opus 4.8 (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Opus 4.8 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 20011 Anthropic Claude Fable 5 (max)33.1% mercor.com for Claude Fable 5 (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Fable 5 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 20012 Anthropic Claude Sonnet 5 (max)39.5% mercor.com for Claude Sonnet 5 (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 20013 Anthropic Claude Opus 5 (max)50.3% mercor.com for Claude Opus 5 (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Opus 5 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 20014 Anthropic Claude Opus 5.5 (max)48.9% mercor.com for Claude Opus 5.5 (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Opus 5.5 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 20015 Anthropic Claude Sonnet 5.5 (max)50.3% mercor.com for Claude Sonnet 5.5 (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 20016 Google (DeepMind) Gemini 3.1 Pro (high)18.0% mercor.com for Gemini 3.1 Pro (high) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 30005 Google (DeepMind) Gemini 3.5 Flash (high)19.6% mercor.com for Gemini 3.5 Flash (high) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.5 Flash on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 30006 Google (DeepMind) Gemini 3.6 Flash (high)32.0% mercor.com for Gemini 3.6 Flash (high) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.6 Flash on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 30007 SpaceXAI Grok 4.5 (high)41.9% mercor.com for Grok 4.5 (high) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Grok 4.5 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 40001 SpaceXAI Grok 4.6 (xhigh)50.3% mercor.com for Grok 4.6 (xhigh) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Grok 4.6 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 40002 SpaceXAI Grok 4.7 (xhigh)47.0% mercor.com for Grok 4.7 (xhigh) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Grok 4.7 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 40003 Meta AI (originally Facebook AI Research) Muse Spark 1.1 (xhigh)3.9% mercor.com for Muse Spark 1.1 (xhigh) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Muse Spark 1.1 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps 80002