- Organizations
- Reka
Reka: AI benchmarks & research
Multimodal model lab. Maintains Vibe-Eval.
Maintained by Reka
1 benchmark- Vibe-Eval
VIBE-Eval is a hard evaluation suite for measuring progress of multimodal language models, consisting of 269 visual understanding prompts with gold-standard responses authored by experts. The benchmark has dual objectives: vibe checking multimodal chat models for day-to-day tasks and rigorously testing frontier models, with the hard set containing >50% questions that all frontier models answer incorrectly.
- Leader
Gemini 2.5 Pro Preview 06-0567.2%
- Models scored
- 8