DelveRL Benchmark

What is DelveRL?

Evaluates local game-playing agents on a deterministic, procedurally generated, partially observed roguelike where agents must secure a key and reach the exit…

Released

2026-08-22

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://github.com/SnyderConsulting/DelveRL

DelveRL code

• Code https://github.com/SnyderConsulting/DelveRL
• Website https://godotengine.org/download/

Which sources cite DelveRL?

• DelveRL

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

• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• AARRI-Bench
• ABC-Bench
• Active-SWE
• ActiveSciBench
• AdaMem-Bench
• AdvancedMathBench