C3-Bench

What is C3-Bench?

C3-Bench evaluates context-aware change captioning with 4,996 human-labeled image pairs across 51 real-world contexts, using an LLM-as-Judge framework scoring…

Released

2026-06-24

Evaluates

General AI, Vision & 3D, cs.CV

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.25445

C3-Bench paper

• Paper https://arxiv.org/abs/2606.25445

Which sources cite C3-Bench?

• C3-Bench

Related General AI, Vision & 3D, cs.CV benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 360CityArena
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench