CODA-BENCH

What is CODA-BENCH?

CODA-Bench is a benchmark for evaluating AI agents on data-intensive analytical tasks in a Linux sandbox with 1,009 tasks across 31 communities, requiring data…

Released

2026-06-13

Evaluates

Agents & Tool Use, General AI, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.15300

CODA-BENCH paper, code and dataset

• Paper https://arxiv.org/abs/2606.15300
• Code https://github.com/ruc-datalab/CoDA-Bench
• Dataset https://huggingface.co/datasets/RUC-DataLab/CoDA-Bench
• Website https://coda-bench.github.io/

Which sources cite CODA-BENCH?

• CODA-BENCH

Related Agents & Tool Use, General AI, cs.AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench
• ActiveSciBench