Results

35 results

SWE-bench Verified — mini-swe-agent results
ProviderModelScoreSourceRegistry No.
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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Gemini 3 Pro on SWE-bench Verified — mini-swe-agent30008
OpenAIGPT-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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for GPT-5.2 on SWE-bench Verified — mini-swe-agent10012
OpenAIGPT-5 mini56.2%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for GPT-5 mini on SWE-bench Verified — mini-swe-agent10019
DeepSeek AIDeepSeek-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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for DeepSeek-V3.2 on SWE-bench Verified — mini-swe-agent110003
Moonshot AIKimi 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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Kimi K2.5 on SWE-bench Verified — mini-swe-agent120001
MiniMaxMiniMax 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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for MiniMax M2.5 on SWE-bench Verified — mini-swe-agent140001
Z.aiGLM-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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for GLM-5 on SWE-bench Verified — mini-swe-agent150002
AnthropicClaude 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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Claude Sonnet 4.5 on SWE-bench Verified — mini-swe-agent20005
AnthropicClaude 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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Claude Haiku 4.5 on SWE-bench Verified — mini-swe-agent20006
AnthropicClaude 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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Claude Opus 4.5 on SWE-bench Verified — mini-swe-agent20007
AnthropicClaude Opus 4.675.6%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Claude Opus 4.6 on SWE-bench Verified — mini-swe-agent20008
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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Gemini 3 Flash on SWE-bench Verified — mini-swe-agent30009
OpenAIGPT-5.269.0%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for GPT-5.2 on SWE-bench Verified — mini-swe-agent10012
Mistral AIDevstral 253.8%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Devstral 2 on SWE-bench Verified — mini-swe-agent90002
Mistral AIDevstral Small 256.4%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Devstral Small 2 on SWE-bench Verified — mini-swe-agent90003
Z.aiGLM-4.655.4%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for GLM-4.6 on SWE-bench Verified — mini-swe-agent150009
MiniMaxMiniMax M261.0%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for MiniMax M2 on SWE-bench Verified — mini-swe-agent140004
AnthropicClaude 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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Claude Opus 4.5 on SWE-bench Verified — mini-swe-agent20007
Google (DeepMind)Gemini 3 Pro74.2%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Gemini 3 Pro on SWE-bench Verified — mini-swe-agent30008
AnthropicClaude Sonnet 4.570.6%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Claude Sonnet 4.5 on SWE-bench Verified — mini-swe-agent20005
Z.aiGLM-4.554.2%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for GLM-4.5 on SWE-bench Verified — mini-swe-agent150007
OpenAIGPT-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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for GPT-5 on SWE-bench Verified — mini-swe-agent10018
OpenAIGPT-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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for GPT-5 mini on SWE-bench Verified — mini-swe-agent10019
OpenAIGPT-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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for GPT-5 nano on SWE-bench Verified — mini-swe-agent10020
OpenAIgpt-oss-120b26.0%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for gpt-oss-120b on SWE-bench Verified — mini-swe-agent15001
AnthropicClaude Opus 467.6%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Claude Opus 4 on SWE-bench Verified — mini-swe-agent20002
OpenAIGPT-4.139.6%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for GPT-4.1 on SWE-bench Verified — mini-swe-agent10002
OpenAIOpenAI o358.4%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for OpenAI o3 on SWE-bench Verified — mini-swe-agent10003
OpenAIOpenAI o4-mini45.0%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for OpenAI o4-mini on SWE-bench Verified — mini-swe-agent10004
AnthropicClaude Sonnet 464.9%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Claude Sonnet 4 on SWE-bench Verified — mini-swe-agent20003
Google (DeepMind)Gemini 2.0 Flash13.5%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Gemini 2.0 Flash on SWE-bench Verified — mini-swe-agent30001
Google (DeepMind)Gemini 2.5 Pro53.6%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Gemini 2.5 Pro on SWE-bench Verified — mini-swe-agent30002
Google (DeepMind)Gemini 2.5 Flash28.7%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Gemini 2.5 Flash on SWE-bench Verified — mini-swe-agent30003
OpenAIGPT-4.1 mini23.9%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for GPT-4.1 mini on SWE-bench Verified — mini-swe-agent10016
AnthropicClaude 3.7 Sonnet52.8%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 TasksReported Benchmark repositorySWE-benchIndependentSWE-bench TeamRecord for Claude 3.7 Sonnet on SWE-bench Verified — mini-swe-agent20001