Our new X account is live! Follow @wizwand_team for updates

Software Engineering on SWE Verified

77.2Resolution Rate

Claude-4.5-Sonnet

Updated 4d ago

Evaluation Results

Method	Links
Claude-4.5-Sonnet 2025.12		77.2	-
Gemini-3.0 Pro 2025.12		76.2	-
GPT-5 High 2025.12		74.9	-
DeepSeek-V3.2 2025.12		73.1	-
Kimi-K2 2025.12		71.3	-
MiniMax M2 2025.12		69.4	-
Claude-3.5-Sonnet 2025.02		53	-
Claude-3.5-Sonnet 2025.02		50.8	-
GPT-4o 2025.02		31.8	-
SoRFT-Qwen-32B 2025.02		30.8	-
Lingma-SWE-GPT-72B 2025.02		30.2	-
SWE-Fixer-Qwen-72B 2025.02		30.2	-
SoRFT-Qwen-7B 2025.02		21.4	-
SWE-Gym-Qwen-32B 2025.02		20.6	-
Lingma-SWE-GPT-7B 2025.02		18.2	-
SWE-Gym-Qwen-14B 2025.02		16.4	-
SWE-Gym-Qwen-7B 2025.02		10.6	-
Claude-3.5-Sonnet-1022 2025.01		-	50.8
GPT-4o-0513 2025.01		-	38.8
DeepSeek-V3 2025.01		-	42
OpenAI-o1-mini 2025.01		-	41.6
OpenAI-o1-1217 2025.01		-	48.9
DeepSeek-R1 2025.01		-	49.2