AARRI-Bench

What is AARRI-Bench?

AARRI-Bench evaluates LLM agents on entry-level research intern tasks, measuring success rate in containerized environments with fixed tasks and scoring.

Released

2026-06-05

Evaluates

General AI, Language & Knowledge, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.07462

AARRI-Bench paper and code

• Paper https://arxiv.org/abs/2606.07462
• Code https://github.com/AARR-bench/AARRI-bench

Which sources cite AARRI-Bench?

• AARRI-Bench

Related General AI, Language & Knowledge, cs.AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• ABC-Bench
• ActBench
• ActiveSciBench