Benchmark
VQAv2 (val)
Vision benchmarks measure how well models understand images. Scores are percentages.
All vision benchmarksScores from LLM Stats data.
- Models measured
- 3
- Scores recorded
- 3
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 68.3%
- Mean
- 71%
- Median
- 4.2%
- Std dev
- 62.4%
- 10th percentile
- 71.6%
- 90th percentile
- 62.4%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Gemma 3 12B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 71.6% |
| 2 | Gemma 3 27B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 71% |
| 3 | Gemma 3 4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 62.4% |
Data credits: Data by LLM Stats