- MMMU Val with chatGPT as a judge 48.2
- AI2D 85
- ChartQA 86.3
- InfoVQA Val 77.4
- OCRBench 839 (out of 1000) 83.9
- OCRBenchV2 English 60.1 / Chinese 37.9 60.1
- DocVQA val 91.2
- VideoMME* (1 tile per image) 54.7
Llama-3.1-Nemotron-Nano-VL-8B-V1
Llama-3.1-Nemotron-Nano-VL-8B-V1.
8
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
NVIDIA Jun 2025 Llama-3.1-Nemotron-Nano-VL-8B-V1
Open weights Small
No Epoch Capabilities Index score yet
- OCRBench v2 56.4% #12 /14
- Video-MME 54.7% #50 /51
- AI2D 85% #37 /52
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ChartQA | 86.3% | #19 of 37 | Lab model card | |
| InfographicVQA | 77.4% | #15 of 26 | Lab model card | |
| AI2D | 85% | #37 of 52 | Lab model card | |
| DocVQA | 91.2% | #26 of 36 | Lab model card | |
| OCRBench v2 | 56.4% | #12 of 14 | Official leaderboard | |
| OCRBench | 83.9% | #30 of 34 | Lab model card | |
| MMMU | 48.2% | #99 of 103 | Lab model card | |
| Video-MME | 54.7% | #50 of 51 | Lab model card |
Its lab's number next to a leaderboard
Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.
| Benchmark | Lab says | Board says | Gap |
|---|---|---|---|
| OCRBench v2 | 60.1% OCRBenchV2 English 60.1 / Chinese 37.9 | 56.4% Leaderboard | +3.7 pts |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.