MTPaperBananaBench

What is MTPaperBananaBench?

Evaluates multi-turn scientific diagram refinement via 292 images annotated with 3,518 user requirements, using a user simulator that provides iterative…

Released

2026-08-31

Evaluates

General AI, Language & Knowledge, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

ai-name-audit-deferred

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.30241

MTPaperBananaBench paper

• Paper https://arxiv.org/abs/2608.30241
• Website https://shirley-wu.github.io/PaperBanana-Interact/

Which sources cite MTPaperBananaBench?

• MTPaperBananaBench

Related General AI, Language & Knowledge, cs.CL 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
• AARRI-Bench
• ABC-Bench
• ActBench