IsoSci Benchmark

What is IsoSci?

IsoSci evaluates reasoning vs. knowledge retrieval in LLMs using isomorphic cross-domain problem pairs, enabling controlled attribution of reasoning gains.

Released

2026-07-01

Evaluates

Factuality, General AI, Information retrieval, Language & Knowledge, Reasoning

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.01431

IsoSci paper and dataset

• Paper https://arxiv.org/abs/2607.01431
• Dataset https://huggingface.co/datasets/isosci/isosci

Which sources cite IsoSci?

• IsoSci

Related Factuality, General AI, Information retrieval, Language & Knowledge, Reasoning benchmarks

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