SciExplore Benchmark

What is SciExplore?

SciExplore evaluates scientific information-seeking and reasoning in LLMs and agents with four task types: scientific database navigation, ambiguous literature…

Released

2026-07-23

Evaluates

General AI, Reasoning, Robotics & Embodied AI

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.20926

SciExplore paper

• Paper https://arxiv.org/abs/2607.20926

Which sources cite SciExplore?

• SciExplore

Related General AI, Reasoning, Robotics & Embodied AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 360CityArena
• 3DCodeBench
• 4DSynth-Nav
• 5-Dialects-BN
• A-OKVQA
• A3S-Bench
• AARRI-Bench