SWE-bench Alternatives

The authoritative AI coding benchmark on real GitHub issues. Here are 12 similar model benchmarks worth considering as SWE-bench alternatives.

• LMArena — Blind-vote LLM battle arena behind the community leaderboard (alternatives)
• OpenCompass — Model Benchmark (alternatives)
• SuperCLUE — Model Benchmark (alternatives)
• C-Eval — Model Benchmark (alternatives)
• CMMLU — Model Benchmark (alternatives)
• FlagEval — Model Benchmark (alternatives)
• AGI-Eval — Model Benchmark (alternatives)
• MMLU — Model Benchmark (alternatives)
• Open LLM Leaderboard — Model Benchmark (alternatives)
• HELM — Stanford's holistic evaluation framework for language models (alternatives)
• MMBench — Model Benchmark (alternatives)
• MagicArena — Model Benchmark (alternatives)

More Model Benchmarks · 中文版