SWE-bench Science

What is SWE-bench Science?

A repository-level benchmark with 119 tasks from 98 GitHub repositories across 20 scientific domains, organized into issue-driven, expert-exploratory, and…

Released

2026-08-20

Evaluates

Code, Code & Software, General AI, Software & AI Compute

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.19799

SWE-bench Science paper

• Paper https://arxiv.org/abs/2608.19799

Which sources cite SWE-bench Science?

• SWE-bench Science

Related Code, Code & Software, General AI, Software & AI Compute benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• Active-SWE
• ActiveSciBench