Benchmark
BLINK - Spatial_Relation
Vision benchmarks measure how well models understand images. Scores are percentages.
All vision benchmarksScores from EvalAI data.
- Models measured
- 4
- Scores recorded
- 4
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 69.6%
- Mean
- 76.2%
- Median
- 8.1%
- Std dev
- 57.3%
- 10th percentile
- 77.6%
- 90th percentile
- 57.3%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Qwen-VL MaxSpatial_Relation· EvalAI data | 77.6% |
| 2 | LLaVA 1.6 34BSpatial_Relation· EvalAI data | 76.2% |
| 3 | Gemini ProSpatial_Relation· EvalAI data | 67.1% |
| 4 | Claude 3 OpusSpatial_Relation· EvalAI data | 57.3% |