Benchmark
VCR_en_easy
Visual Commonsense Reasoning (VCR) benchmark that tests higher-order cognition and commonsense reasoning beyond simple object recognition. Models must…
- Modality
- multimodal
- Categories
- reasoning, vision
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 1
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen2-VL-72B-Instruct | Qwen | 0.9193 | 2024-08-29 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.