Benchmark
ViDoRe(v3) - Public split
Vision benchmarks measure how well models understand images. Scores are percentages.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 1.82
Score distribution
- 54.2%
- Mean
- 58%
- Median
- 6.1%
- Std dev
- 45.7%
- 10th percentile
- 60.4%
- 90th percentile
- 45.7%
- Min
This benchmark has a weight of 1.82 for embedding models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Nemotron 3.5 Embed 8bPublic split· MTEB Multimodal Boards data docs | 60.4% |
| 2 | Qwen3-VL Embedding 8BPublic split· MTEB Multimodal Boards data docs | 58.3% |
| 3 | Nemotron 3.5 Embed 1bPublic split· MTEB Multimodal Boards data docs | 58% |
| 4 | Jina Embeddings v4Public split· MTEB Multimodal Boards data docs | 57% |
| 5 | Jina Embeddings v5 Omni NanoPublic split· MTEB Multimodal Boards data docs | 45.7% |
| 6 | Jina Embeddings v5 Omni SmallPublic split· MTEB Multimodal Boards data docs | 45.7% |