SWE-Serve Benchmark

What is SWE-Serve?

Pending verification of task definition and scoring contract for production inference serving agent evaluation.

Released

2026-09-22

Evaluates

Language & Knowledge, Software & AI Compute, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

ai-name-audit-deferred

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.26777

SWE-Serve paper

• Paper https://arxiv.org/abs/2609.26777

Which sources cite SWE-Serve?

• SWE-Serve

Related Language & Knowledge, Software & AI Compute, cs.AI benchmarks

• 2d-fet-bench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• AARRI-Bench
• ABACUS
• ABC-Bench
• Active-SWE
• ActiveSciBench