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
41–60 / 90
1,441.405
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Software And It Services
- dimension
- general
- metric
- Arena rating
- rank
- 121
- 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
- 1425.9582249205869
- confidence upper
- 1456.8525218553848
Original result ↗1,391.118
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Entertainment And Sports And Media
- dimension
- factuality
- metric
- Arena rating
- rank
- 121
- sample size
- 1112
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1376.3026389395945
- confidence upper
- 1405.932600857302
Original result ↗1,445.185
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Life And Physical And Social Science
- dimension
- style
- metric
- Arena rating
- rank
- 124
- sample size
- 664
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1422.2246842057557
- confidence upper
- 1468.1461968437634
Original result ↗1,471.711
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Coding
- dimension
- factuality
- metric
- Arena rating
- rank
- 125
- sample size
- 972
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1455.3220642081185
- confidence upper
- 1488.0995363934999
Original result ↗1,426.162
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Overall
- dimension
- factuality
- metric
- Arena rating
- rank
- 126
- sample size
- 4061
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1418.2384284617947
- confidence upper
- 1434.0864737210425
Original result ↗1,420.279
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Exclude Ties
- dimension
- factuality
- metric
- Arena rating
- rank
- 126
- sample size
- 3064
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1409.9926999565373
- confidence upper
- 1430.5646756198225
Original result ↗1,416.602
- source id
- lmarena
- leaderboard name
- LMArena Text Multi Turn
- dimension
- general
- metric
- Arena rating
- rank
- 126
- sample size
- 621
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1392.7142845739113
- confidence upper
- 1440.4905302003021
Original result ↗1,460.041
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Software And It Services
- dimension
- style
- metric
- Arena rating
- rank
- 127
- 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
- 1444.511862701964
- confidence upper
- 1475.5699894832815
Original result ↗1,426.241
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Multi Turn
- dimension
- style
- metric
- Arena rating
- rank
- 128
- sample size
- 621
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1402.2263988458908
- confidence upper
- 1450.2559905569356
Original result ↗1,428.531
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Longer Query
- dimension
- factuality
- metric
- Arena rating
- rank
- 130
- sample size
- 1743
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1416.462185318705
- confidence upper
- 1440.5998034403403
Original result ↗1,411.141
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Non English
- dimension
- factuality
- metric
- Arena rating
- rank
- 130
- sample size
- 2511
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1400.9420435265752
- confidence upper
- 1421.3407337633125
Original result ↗1,448.624
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Hard Prompts English
- dimension
- style
- metric
- Arena rating
- rank
- 132
- 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
- 1429.7581789209687
- confidence upper
- 1467.4890480734377
Original result ↗1,445.647
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Hard Prompts
- dimension
- factuality
- metric
- Arena rating
- rank
- 132
- sample size
- 2525
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1435.6655970329707
- confidence upper
- 1455.6281890362625
Original result ↗1,401.061
- source id
- lmarena
- leaderboard name
- LMArena Text Instruction Following
- dimension
- general
- metric
- Arena rating
- rank
- 132
- 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
- 1384.7898318083767
- confidence upper
- 1417.3325916037504
Original result ↗1,428.953
- source id
- lmarena
- leaderboard name
- LMArena Text Hard Prompts English
- dimension
- general
- metric
- Arena rating
- rank
- 133
- 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
- 1410.1935857340532
- confidence upper
- 1447.7132506873918
Original result ↗1,428.218
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Life And Physical And Social Science
- dimension
- general
- metric
- Arena rating
- rank
- 133
- sample size
- 664
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1405.4543417599057
- confidence upper
- 1450.9820593983818
Original result ↗1,454.85
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Chinese
- dimension
- style
- metric
- Arena rating
- rank
- 134
- 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
- 1418.4060329631436
- confidence upper
- 1491.2940697105882
Original result ↗1,422.369
- source id
- lmarena
- leaderboard name
- LMArena Text Expert
- dimension
- general
- metric
- Arena rating
- rank
- 134
- sample size
- 424
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1394.3798262124608
- confidence upper
- 1450.3590145378366
Original result ↗1,411.44
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Instruction Following
- dimension
- style
- metric
- Arena rating
- rank
- 134
- 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
- 1395.1250201522885
- confidence upper
- 1427.754879189219
Original result ↗1,379.006
- source id
- lmarena
- leaderboard name
- LMArena Text Creative Writing
- dimension
- general
- metric
- Arena rating
- rank
- 134
- sample size
- 926
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
- confidence lower
- 1358.6030082652908
- confidence upper
- 1399.409188193477
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