Benchmark
BLINK - Relative_Reflectance
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
- 38.2%
- Mean
- 46.3%
- Median
- 9.6%
- Std dev
- 27.6%
- 10th percentile
- 49.3%
- 90th percentile
- 27.6%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Qwen-VL MaxRelative_Reflectance· EvalAI data | 49.3% |
| 2 | Gemini ProRelative_Reflectance· EvalAI data | 46.3% |
| 3 | LLaVA 1.6 34BRelative_Reflectance· EvalAI data | 29.9% |
| 4 | Claude 3 OpusRelative_Reflectance· EvalAI data | 27.6% |