Benchmark
VLMsAreBlind
A vision-language benchmark that probes blind spots and brittle reasoning in multimodal models.
- Modality
- multimodal
- Categories
- multimodal, reasoning, vision
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 4
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen3.5-122B-A10B | Qwen | 0.967 | 2026-02-24 | evidence |
| Qwen3.5-27B | Qwen | 0.969 | 2026-02-24 | evidence |
| Qwen3.5-35B-A3B | Qwen | 0.97 | 2026-02-24 | evidence |
| Qwen3.6-27B | Qwen | 0.97 | 2026-04-21 | 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.