Benchmark
BLINK - Relative_Depth
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
- 57.7%
- Mean
- 58.9%
- Median
- 5.2%
- Std dev
- 50%
- 10th percentile
- 64.5%
- 90th percentile
- 50%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | LLaVA 1.6 34BRelative_Depth· EvalAI data | 64.5% |
| 2 | Qwen-VL MaxRelative_Depth· EvalAI data | 58.9% |
| 3 | Claude 3 OpusRelative_Depth· EvalAI data | 57.3% |
| 4 | Gemini ProRelative_Depth· EvalAI data | 50% |