SciFigBench

What is SciFigBench?

SciFigBench is a diagnostic VLM benchmark for scientific figure understanding, covering perception, reasoning, and behavioral reliability under uncertainty.

Released

2026-08-13

Evaluates

General AI, Language & Knowledge, Reasoning

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.13267

SciFigBench paper

• Paper https://arxiv.org/abs/2608.13267
• Website https://scifigbench.nlp4sci.com

Which sources cite SciFigBench?

• SciFigBench

Related General AI, 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