OpenAI GPT-5.4 (xhigh)78.1% mercor.com for GPT-5.4 (xhigh) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-5.4 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 10007 OpenAI GPT-5.5 (xhigh)78.8% mercor.com for GPT-5.5 (xhigh) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-5.5 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 10008 OpenAI GPT-5.6 Luna (max)76.2% mercor.com for GPT-5.6 Luna (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-5.6 Luna on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 10009 OpenAI GPT-5.6 Terra (max)77.8% mercor.com for GPT-5.6 Terra (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-5.6 Terra on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 10011 OpenAI GPT-6 Luna (max)76.1% mercor.com for GPT-6 Luna (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-6 Luna on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 10013 OpenAI GPT-6 Sol (max)80.3% mercor.com for GPT-6 Sol (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-6 Sol on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 10014 OpenAI GPT-6.1 Sol (max)87.3% mercor.com for GPT-6.1 Sol (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GPT-6.1 Sol on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 10015 DeepSeek AI DeepSeek-V4-Pro (max)75.4% mercor.com for DeepSeek-V4-Pro (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for DeepSeek-V4-Pro on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 110002 DeepSeek AI DeepSeek-V3.2 66.0% mercor.com for DeepSeek-V3.2 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for DeepSeek-V3.2 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 110003 Moonshot AI Kimi K3 (max)83.3% mercor.com for Kimi K3 (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Kimi K3 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 120003 Alibaba (Tongyi) Qwen3.5-397B-A17B 72.1% mercor.com for Qwen3.5-397B-A17B on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Qwen3.5-397B-A17B on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 130003 Alibaba (Tongyi) Qwen3.8-Max (xhigh)83.6% mercor.com for Qwen3.8-Max (xhigh) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Qwen3.8-Max on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 130008 MiniMax MiniMax M2.7 (high)75.3% mercor.com for MiniMax M2.7 (high) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for MiniMax M2.7 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 140002 MiniMax MiniMax M3 (high)75.5% mercor.com for MiniMax M3 (high) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for MiniMax M3 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 140003 Z.ai GLM-5.2 (max)78.5% mercor.com for GLM-5.2 (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.2 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 150004 Z.ai GLM-5.3 (max)81.7% mercor.com for GLM-5.3 (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.3 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 150005 Anthropic Claude Fable 5.1 (high)92.1% mercor.com for Claude Fable 5.1 (high) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Fable 5.1 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 20004 Anthropic Claude Fable 5.1 (max)96.6% mercor.com for Claude Fable 5.1 (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Fable 5.1 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 20004 Anthropic Claude Sonnet 4.6 (high)79.1% mercor.com for Claude Sonnet 4.6 (high) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 4.6 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 20009 Anthropic Claude Opus 4.7 (max)83.1% mercor.com for Claude Opus 4.7 (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Opus 4.7 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 20010 Anthropic Claude Opus 4.8 (max)88.5% mercor.com for Claude Opus 4.8 (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Opus 4.8 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 20011 Anthropic Claude Fable 5 (max)95.9% mercor.com for Claude Fable 5 (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Fable 5 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 20012 Anthropic Claude Sonnet 5 (max)82.8% mercor.com for Claude Sonnet 5 (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 20013 Anthropic Claude Opus 5 (max)93.5% mercor.com for Claude Opus 5 (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Opus 5 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 20014 Anthropic Claude Opus 5.5 (max)98.2% mercor.com for Claude Opus 5.5 (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Opus 5.5 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 20015 Anthropic Claude Sonnet 5.5 (max)96.7% mercor.com for Claude Sonnet 5.5 (max) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Claude Sonnet 5.5 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 20016 Google (DeepMind) Gemini 3.8 Flash (high)80.6% mercor.com for Gemini 3.8 Flash (high) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.8 Flash on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 30004 Google (DeepMind) Gemini 3.1 Pro (high)78.4% mercor.com for Gemini 3.1 Pro (high) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 30005 Google (DeepMind) Gemini 3.5 Flash (high)78.5% mercor.com for Gemini 3.5 Flash (high) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.5 Flash on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 30006 Google (DeepMind) Gemini 3.6 Flash (high)81.1% mercor.com for Gemini 3.6 Flash (high) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.6 Flash on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 30007 Google (DeepMind) Gemini 3.7 Flash (high)81.0% mercor.com for Gemini 3.7 Flash (high) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.7 Flash on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 30010 Google (DeepMind) Gemma 4 31B Instruct 46.1% mercor.com for Gemma 4 31B Instruct on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemma 4 31B Instruct on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 35002 SpaceXAI Grok 4.5 (high)81.7% mercor.com for Grok 4.5 (high) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Grok 4.5 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 40001 SpaceXAI Grok 4.6 (xhigh)84.6% mercor.com for Grok 4.6 (xhigh) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Grok 4.6 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 40002 SpaceXAI Grok 4.7 (xhigh)79.1% mercor.com for Grok 4.7 (xhigh) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Grok 4.7 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps 40003