MineExplorer Benchmark

What is MineExplorer?

A Minecraft benchmark that composes atomic tasks into implicit multi-hop exploration tasks for MLLM agents, scored by rule-based milestone evaluators.

Released

2026-05-29

Evaluates

Language & Knowledge, Robotics & Embodied AI, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2605.30931

MineExplorer paper and code

• Paper https://arxiv.org/abs/2605.30931
• Code https://github.com/Jometeorie/MineExplorer

Which sources cite MineExplorer?

• MineExplorer

Related Language & Knowledge, Robotics & Embodied AI, cs.CL benchmarks

• 360CityArena
• 4DSynth-Nav
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• AARRI-Bench
• ABC-Bench
• ActiveFly-Bench
• ActiveSciBench