FPCO-Dialog Benchmark
Explore score history ↗A benchmark with 1,080 images and 10,800 question turns across 10-turn dialogues, evaluating correction and cooperation when false visual premises recur, scored by CorrTP@K and two detectors.
- Released
- 2026-09-03
- Evaluates
- General AI, Multimodal
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
FPCO-Dialog paper and code
No reported scores are on record for this benchmark yet.