Multi-SWE-Bench

Multi-SWE-Bench - Benchmark Leaderboard & Model Performance | AI Stats

Models Using This Benchmark

Organisation	Model	Reported	Top Score	Info	Self Reported	Source
MiniMax	MiniMax M2.7	18 Mar 2026	52.70	LLM Stats (ZeroEval)	Yes	Source
MiniMax	MiniMax M2.5	12 Feb 2026	51.30	LLM Stats (ZeroEval)	Yes	Source
MiniMax	MiniMax M2.1	23 Dec 2025	49.40	LLM Stats (ZeroEval)	Yes	Source
ByteDance	Seed 2.0 Pro	14 Feb 2026	45.20	Seed2 official benchmark table \| Multi-SWE-Bench	Yes	Source
Moonshot	Kimi K2 Thinking	06 Nov 2025	41.90	LLM Stats (ZeroEval) \| inferred alias from kimi-k2-thinking-0905	Yes	Source
ByteDance	Seed 2.0 Lite	14 Feb 2026	41.10	Seed2 official benchmark table \| Multi-SWE-Bench	Yes	Source
MiniMax	MiniMax M2	27 Oct 2025	36.20	LLM Stats (ZeroEval)	Yes	Source
MiniMax	MiniMax M2 Her	24 Jan 2026	36.20	LLM Stats (ZeroEval) \| inferred modality/version alias from minimax-m2	Yes	Source