Verus-SpecBench

What is Verus-SpecBench?

Verus-SpecBench has 581 tasks in which agents write formal Verus specifications for Codeforces problems. Specs are executed and tested against official tests…

Released

2026-05-26

Evaluates

Code & Software, General AI, cs.SE

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2605.26457

Verus-SpecBench paper and code

• Paper https://arxiv.org/abs/2605.26457
• Code https://github.com/formal-verif-is-cool/verus-spec-gym

Which sources cite Verus-SpecBench?

• Verus-SpecBench

Related Code & Software, General AI, cs.SE 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