Google (DeepMind) Gemini 3 Pro (high)69.6% github.com for Gemini 3 Pro (high) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 26, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for Gemini 3 Pro on SWE-bench Verified — mini-swe-agent 30008 OpenAI GPT-5.2 (high)72.8% github.com for GPT-5.2 (high) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 17, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for GPT-5.2 on SWE-bench Verified — mini-swe-agent 10012 OpenAI GPT-5 mini 56.2% github.com for GPT-5 mini on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 17, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for GPT-5 mini on SWE-bench Verified — mini-swe-agent 10019 DeepSeek AI DeepSeek-V3.2 (high)70.0% github.com for DeepSeek-V3.2 (high) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 17, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for DeepSeek-V3.2 on SWE-bench Verified — mini-swe-agent 110003 Moonshot AI Kimi K2.5 (high)70.8% github.com for Kimi K2.5 (high) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 17, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for Kimi K2.5 on SWE-bench Verified — mini-swe-agent 120001 MiniMax MiniMax M2.5 (high)75.8% github.com for MiniMax M2.5 (high) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 17, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for MiniMax M2.5 on SWE-bench Verified — mini-swe-agent 140001 Z.ai GLM-5 (high)72.8% github.com for GLM-5 (high) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 17, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for GLM-5 on SWE-bench Verified — mini-swe-agent 150002 Anthropic Claude Sonnet 4.5 (high)71.4% github.com for Claude Sonnet 4.5 (high) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 17, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for Claude Sonnet 4.5 on SWE-bench Verified — mini-swe-agent 20005 Anthropic Claude Haiku 4.5 (high)66.6% github.com for Claude Haiku 4.5 (high) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 17, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for Claude Haiku 4.5 on SWE-bench Verified — mini-swe-agent 20006 Anthropic Claude Opus 4.5 (high)76.8% github.com for Claude Opus 4.5 (high) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 17, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for Claude Opus 4.5 on SWE-bench Verified — mini-swe-agent 20007 Anthropic Claude Opus 4.6 75.6% github.com for Claude Opus 4.6 on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 17, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for Claude Opus 4.6 on SWE-bench Verified — mini-swe-agent 20008 Google (DeepMind) Gemini 3 Flash (high)75.8% github.com for Gemini 3 Flash (high) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 17, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for Gemini 3 Flash on SWE-bench Verified — mini-swe-agent 30009 OpenAI GPT-5.2 69.0% github.com for GPT-5.2 on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported December 11, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for GPT-5.2 on SWE-bench Verified — mini-swe-agent 10012 Mistral AI Devstral 2 53.8% github.com for Devstral 2 on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported December 9, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for Devstral 2 on SWE-bench Verified — mini-swe-agent 90002 Mistral AI Devstral Small 2 56.4% github.com for Devstral Small 2 on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported December 9, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for Devstral Small 2 on SWE-bench Verified — mini-swe-agent 90003 Z.ai GLM-4.6 55.4% github.com for GLM-4.6 on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported December 1, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for GLM-4.6 on SWE-bench Verified — mini-swe-agent 150009 MiniMax MiniMax M2 61.0% github.com for MiniMax M2 on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported November 24, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for MiniMax M2 on SWE-bench Verified — mini-swe-agent 140004 Anthropic Claude Opus 4.5 (medium)74.4% github.com for Claude Opus 4.5 (medium) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported November 24, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for Claude Opus 4.5 on SWE-bench Verified — mini-swe-agent 20007 Google (DeepMind) Gemini 3 Pro 74.2% github.com for Gemini 3 Pro on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported November 18, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for Gemini 3 Pro on SWE-bench Verified — mini-swe-agent 30008 Anthropic Claude Sonnet 4.5 70.6% github.com for Claude Sonnet 4.5 on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported September 29, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for Claude Sonnet 4.5 on SWE-bench Verified — mini-swe-agent 20005 Z.ai GLM-4.5 54.2% github.com for GLM-4.5 on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported August 22, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for GLM-4.5 on SWE-bench Verified — mini-swe-agent 150007 OpenAI GPT-5 (medium)65.0% github.com for GPT-5 (medium) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported August 7, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for GPT-5 on SWE-bench Verified — mini-swe-agent 10018 OpenAI GPT-5 mini (medium)59.8% github.com for GPT-5 mini (medium) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported August 7, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for GPT-5 mini on SWE-bench Verified — mini-swe-agent 10019 OpenAI GPT-5 nano (medium)34.8% github.com for GPT-5 nano (medium) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported August 7, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for GPT-5 nano on SWE-bench Verified — mini-swe-agent 10020 OpenAI gpt-oss-120b 26.0% github.com for gpt-oss-120b on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported August 7, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for gpt-oss-120b on SWE-bench Verified — mini-swe-agent 15001 Anthropic Claude Opus 4 67.6% github.com for Claude Opus 4 on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported August 2, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for Claude Opus 4 on SWE-bench Verified — mini-swe-agent 20002 OpenAI GPT-4.1 39.6% github.com for GPT-4.1 on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported July 26, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for GPT-4.1 on SWE-bench Verified — mini-swe-agent 10002 OpenAI OpenAI o3 58.4% github.com for OpenAI o3 on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported July 26, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for OpenAI o3 on SWE-bench Verified — mini-swe-agent 10003 OpenAI OpenAI o4-mini 45.0% github.com for OpenAI o4-mini on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported July 26, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for OpenAI o4-mini on SWE-bench Verified — mini-swe-agent 10004 Anthropic Claude Sonnet 4 64.9% github.com for Claude Sonnet 4 on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported July 26, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for Claude Sonnet 4 on SWE-bench Verified — mini-swe-agent 20003 Google (DeepMind) Gemini 2.0 Flash 13.5% github.com for Gemini 2.0 Flash on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported July 26, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for Gemini 2.0 Flash on SWE-bench Verified — mini-swe-agent 30001 Google (DeepMind) Gemini 2.5 Pro 53.6% github.com for Gemini 2.5 Pro on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported July 26, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for Gemini 2.5 Pro on SWE-bench Verified — mini-swe-agent 30002 Google (DeepMind) Gemini 2.5 Flash 28.7% github.com for Gemini 2.5 Flash on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported July 26, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for Gemini 2.5 Flash on SWE-bench Verified — mini-swe-agent 30003 OpenAI GPT-4.1 mini 23.9% github.com for GPT-4.1 mini on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported July 20, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for GPT-4.1 mini on SWE-bench Verified — mini-swe-agent 10016 Anthropic Claude 3.7 Sonnet 52.8% github.com for Claude 3.7 Sonnet on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported July 20, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for Claude 3.7 Sonnet on SWE-bench Verified — mini-swe-agent 20001