SWE-bench Verified

Name: SWE-bench Verified — AI Model Benchmark Results
Creator: Neura Market

Real-world GitHub issue resolution — 500 verified problems from popular Python repos.

Model Rankings (121)

#	Model	Score	Provider	Source
	Claude Fable 5🇺🇸			verified
	Claude Mythos Preview🇺🇸			verified
	Claude Opus 4.8🇺🇸			verified
	Claude Opus 4.7🇺🇸			verified
	Claude Sonnet 5🇺🇸			verified
	Claude Opus 4.5🇺🇸			verified
	Claude Opus 4.6🇺🇸			verified
	DeepSeek-V4-Pro-Max🇨🇳			verified
	Gemini 3.1 Pro🇺🇸			verified
	MiniMax M3🇨🇳			verified
	Q Qwen3.7 Max🇨🇳			verified
	M Kimi K2.6🇨🇳			verified
	MiniMax M2.5🇨🇳			verified
	T Inkling-Small🇺🇸			verified
	GPT-5.2🇺🇸			verified
	Claude Sonnet 4.6🇺🇸			verified
	DeepSeek-V4-Flash-Max🇨🇳			verified
	X MiMo-V2.5-Pro🇨🇳			verified
	Q Qwen3.6 Plus🇨🇳			verified
	DeepSeek-V4-Flash-0423🇨🇳			verified
	X MiMo-V2-Pro🇨🇳			verified
	T Hy3🇨🇳			verified
	Gemini 3 Flash🇺🇸			verified
	Z GLM-5🇨🇳			verified
	Q Qwen3.7-Plus🇨🇳			verified
	Mistral Medium 3.5🇫🇷			verified
	M Muse Spark🇺🇸			verified
	Q Qwen3.6-27B🇨🇳			verified
	M Kimi K2.5🇨🇳			verified
	B Seed 2.0 Pro🇨🇳			verified
	Q Qwen3.5-397B-A17B🇨🇳			verified
	GPT-5.1🇺🇸			verified
	GPT-5.1 Instant🇺🇸			verified
	GPT-5.1 Thinking🇺🇸			verified
	Gemini 3 Pro🇺🇸			verified
	M Muse Glimmer-30B🇺🇸			verified
	GPT-5🇺🇸			verified
	X MiMo-V2-Omni🇨🇳			verified
	Claude Opus 4.1🇺🇸			verified
	GPT-5 Codex🇺🇸			verified
	S Step-3.5-Flash🇨🇳			verified
	Z GLM-4.7🇨🇳			verified
	GPT-5.1 Codex🇺🇸			verified
	B Seed 2.0 Lite🇨🇳			verified
	MAI-Thinking-1🇺🇸			verified
	Q Qwen3.6-35B-A3B🇨🇳			verified
	X MiMo-V2-Flash🇨🇳			verified
	Claude Haiku 4.5🇺🇸			verified
	DeepSeek-V3.2-Speciale🇨🇳			verified
	DeepSeek-V3.2 (Thinking)🇨🇳			verified
	DeepSeek-V3.2🇨🇳			verified
	Claude Code🇺🇸			aggregated
	Claude Sonnet 4🇺🇸			verified
	MAI-Code-1.1-Flash🇺🇸			verified
	Claude Opus 4🇺🇸			verified
	Q Qwen3.5-27B🇨🇳			verified
	Q Qwen3.5-122B-A10B🇨🇳			verified
	MAI-Code-1-Flash🇺🇸			verified
	M Kimi K2-Thinking-0905🇨🇳			verified
	P Laguna XS 2.1🇺🇸			verified
	X Grok Code Fast 1🇺🇸			verified
	Nemotron 3 Ultra (550B A55B)🇺🇸			verified
	U Solar Pro 4🇰🇷			verified
	Claude 3.7 Sonnet🇺🇸			verified
	Nova 2 Pro🇺🇸			verified
	M LongCat-Flash-Thinking-2601🇨🇳			verified
	Q Qwen3-Coder 480B A35B Instruct🇨🇳			verified
	Q Qwen3 Max🇨🇳			verified
	MiniMax M2🇨🇳			verified
	Q Qwen3.5-35B-A3B🇨🇳			verified
	o3🇺🇸			verified
	OpenAI Codex🇺🇸			aggregated
	o4-mini🇺🇸			verified
	Z GLM-4.6🇨🇳			verified
	DeepSeek-V3.2-Exp🇨🇳			verified
	North Mini Code 1.0🇨🇦			verified
	Gemini 2.5 Pro Preview 06-05🇺🇸			verified
	MiniMax M2.1🇨🇳			verified
	DeepSeek-V3.1🇨🇳			verified
	M Kimi K2-Instruct-0905🇨🇳			verified
	Nova 2 Lite🇺🇸			verified
	Z GLM-4.5🇨🇳			verified
	Gemini 2.5 Pro🇺🇸			verified
	Devstral Medium🇫🇷			verified
	M LongCat-Flash-Chat🇨🇳			verified
	Gemini 2.5 Flash🇺🇸			verified
	M LongCat-Flash-Thinking🇨🇳			verified
	Z GLM-4.7-Flash🇨🇳			verified
	Z GLM-4.5-Air🇨🇳			verified
	I IBM Granite 4.2 30B🇺🇸			verified
	MiniMax M1 80K🇨🇳			verified
	Claude Opus 4🇺🇸			aggregated
	MiniMax M1 40K🇨🇳			verified
	GPT-4.1🇺🇸			verified
	M LongCat-Flash-Lite🇨🇳			verified
	Nemotron 3 Super (120B A12B)🇺🇸			verified
	Devstral Small 1.1🇫🇷			verified
	Claude Sonnet 4🇺🇸			aggregated
	Nemotron 3.5 Lightning (30B A3B)🇺🇸			verified
	o3-mini🇺🇸			verified
	Claude 3.5 Sonnet🇺🇸			verified
	Claude 3.5 Sonnet🇺🇸			aggregated
	o1🇺🇸			aggregated
	I IBM Granite 4.2 8B🇺🇸			verified
	S Sarvam-105B🇮🇳			verified
	DeepSeek-R1-0528🇨🇳			verified
	DeepSeek-V3🇨🇳			verified
	o1-preview🇺🇸			verified
	o1🇺🇸			verified
	Claude 3.5 Haiku🇺🇸			verified
	Nemotron 3 Nano (30B A3B)🇺🇸			verified
	GPT-4.5🇺🇸			verified
	S Sarvam-30B🇮🇳			verified
	GPT-4o🇺🇸			verified
	GPT-4o🇺🇸			aggregated
	Gemini 2.5 Flash-Lite🇺🇸			verified
	Devin🇺🇸			aggregated
	GPT-4.1 mini🇺🇸			verified
	Gemini Diffusion🇺🇸			verified
	DeepSeek-V2.5🇨🇳			verified
	GPT-4o mini🇺🇸			verified

AI Model Benchmarks

SWE-bench Verified

Model Rankings (121)