nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4
NVFP4 vision-language reasoning model for document understanding, coding, and tool use.
azureFoundry/azure-huggingface/nvidia--nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4@1
NVFP4 vision-language reasoning model for document understanding, coding, and tool use.
Specifications & capabilities
- Input
- text, image, video
- Output
- text
- Context window · tokens
- 1048576
- Published model ID
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4
- Capabilities
- multimodal, visionInput
Evaluations
21–40 / 90
1,195.13
- source id
- lmarena
- leaderboard name
- LMArena Vision Creative Writing Vision
- dimension
- multimodal
- metric
- Arena rating
- rank
- 87
- sample size
- 473
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1165.48318098284
- confidence upper
- 1224.7763711078062
Original result ↗1,223.771
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control Chinese
- dimension
- multimodal
- metric
- Arena rating
- rank
- 88
- sample size
- 281
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1186.2788012271849
- confidence upper
- 1261.2629108149467
Original result ↗1,233.312
- source id
- lmarena
- leaderboard name
- LMArena Vision Style Control Homework
- dimension
- multimodal
- metric
- Arena rating
- rank
- 89
- sample size
- 800
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1211.507623051705
- confidence upper
- 1255.1168369302134
Original result ↗1,228.545
- source id
- lmarena
- leaderboard name
- LMArena Vision Homework
- dimension
- multimodal
- metric
- Arena rating
- rank
- 90
- sample size
- 800
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1206.6006737528185
- confidence upper
- 1250.4892040659101
Original result ↗1,227.615
- source id
- lmarena
- leaderboard name
- LMArena Vision Chinese
- dimension
- multimodal
- metric
- Arena rating
- rank
- 90
- sample size
- 281
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1189.7841145818145
- confidence upper
- 1265.4460233231077
Original result ↗1,443.045
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Business And Management And Financial Operations
- dimension
- factuality
- metric
- Arena rating
- rank
- 92
- sample size
- 635
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1422.0398955956227
- confidence upper
- 1464.0502305883165
Original result ↗1,393.496
- source id
- lmarena
- leaderboard name
- LMArena Webdev Webdev React
- dimension
- coding
- metric
- Arena rating
- rank
- 98
- sample size
- 3317
- evaluated at
- 2026-11-10T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1380.0025008503055
- confidence upper
- 1406.9902770555732
Original result ↗1,418.708
- source id
- lmarena
- leaderboard name
- LMArena Webdev Webdev Html
- dimension
- coding
- metric
- Arena rating
- rank
- 100
- sample size
- 716
- evaluated at
- 2026-11-10T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1392.365389228368
- confidence upper
- 1445.0497305328788
Original result ↗1,401.279
- source id
- lmarena
- leaderboard name
- LMArena Webdev Webdev
- dimension
- coding
- metric
- Arena rating
- rank
- 102
- sample size
- 5056
- evaluated at
- 2026-11-10T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1390.5059490384292
- confidence upper
- 1412.0530298587105
Original result ↗1,401.279
- source id
- lmarena
- leaderboard name
- LMArena Webdev Overall
- dimension
- coding
- metric
- Arena rating
- rank
- 102
- sample size
- 5056
- evaluated at
- 2026-11-10T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1390.5059490384292
- confidence upper
- 1412.0530298587105
Original result ↗1,445.975
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality English
- dimension
- factuality
- metric
- Arena rating
- rank
- 105
- sample size
- 1550
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1433.817955848454
- confidence upper
- 1458.1317617744585
Original result ↗1,428.983
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Russian
- dimension
- factuality
- metric
- Arena rating
- rank
- 107
- sample size
- 550
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1404.6832208234737
- confidence upper
- 1453.2819250391167
Original result ↗1,401.271
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Creative Writing
- dimension
- factuality
- metric
- Arena rating
- rank
- 108
- sample size
- 922
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1385.9695269965048
- confidence upper
- 1416.5720881897012
Original result ↗1,425.306
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Instruction Following
- dimension
- factuality
- metric
- Arena rating
- rank
- 110
- sample size
- 1373
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1411.7599882018758
- confidence upper
- 1438.8515535367487
Original result ↗1,463.948
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Hard Prompts English
- dimension
- factuality
- metric
- Arena rating
- rank
- 112
- sample size
- 996
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1448.5075933887979
- confidence upper
- 1479.3889983732965
Original result ↗1,441.296
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control English
- dimension
- style
- metric
- Arena rating
- rank
- 115
- sample size
- 1550
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1426.2960592739164
- confidence upper
- 1456.2960323506486
Original result ↗1,467.95
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Software And It Services
- dimension
- factuality
- metric
- Arena rating
- rank
- 117
- sample size
- 1442
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1454.8578148516754
- confidence upper
- 1481.0415244672133
Original result ↗1,407.086
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Writing And Literature And Language
- dimension
- factuality
- metric
- Arena rating
- rank
- 117
- sample size
- 1157
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1392.7292766854614
- confidence upper
- 1421.442722497385
Original result ↗1,430.76
- source id
- lmarena
- leaderboard name
- LMArena Text English
- dimension
- general
- metric
- Arena rating
- rank
- 118
- sample size
- 1550
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1415.7449754525057
- confidence upper
- 1445.7755351013757
Original result ↗1,455.792
- source id
- lmarena
- leaderboard name
- LMArena Text Chinese
- dimension
- general
- metric
- Arena rating
- rank
- 121
- sample size
- 272
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1419.7316457703432
- confidence upper
- 1491.8513546358631
Original result ↗Provider specifications & access
1–1 / 1
- source model id
- azure-huggingface/nvidia--nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4@1
- hosting
- foundry-managed-compute
- license
- other
- context length
- 1048576
Source specification observations
1–1 / 1
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
Explore more models