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

1–20 / 90

LMArena

-0.121

source id
lmarena
leaderboard name
LMArena Agent Bash Reliability Overall
dimension
general
metric
Arena score
rank
55
sample size
6016
evaluated at
2026-11-11T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
-0.1338020369339486
confidence upper
-0.10794325942177145
Original result ↗

LMArena

-0.189

source id
lmarena
leaderboard name
LMArena Agent Task Outcome Explicit Overall
dimension
agentic
metric
Arena score
rank
55
sample size
12621
evaluated at
2026-11-11T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
-0.20880730345022105
confidence upper
-0.16907807015816786
Original result ↗

LMArena

-0.16

source id
lmarena
leaderboard name
LMArena Agent Overall
dimension
agentic
metric
Arena score
rank
56
sample size
33650
evaluated at
2026-11-11T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
-0.16730921323402187
confidence upper
-0.1525722244139664
Original result ↗

LMArena

-0.17

source id
lmarena
leaderboard name
LMArena Agent Steerability Overall
dimension
agentic
metric
Arena score
rank
56
sample size
23871
evaluated at
2026-11-11T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
-0.18206826990628466
confidence upper
-0.15827558248159923
Original result ↗

LMArena

-0.235

source id
lmarena
leaderboard name
LMArena Agent Praise Complaint Overall
dimension
agentic
metric
Arena score
rank
57
sample size
8142
evaluated at
2026-11-11T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
-0.25060850888585484
confidence upper
-0.22019027720107656
Original result ↗

LMArena

-0.065

source id
lmarena
leaderboard name
LMArena Agent Tool Hallucination Overall
dimension
agentic
metric
Arena score
rank
59
sample size
30603
evaluated at
2026-11-11T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
-0.07547712408465089
confidence upper
-0.05408868507023214
Original result ↗

LMArena

1,391.78

source id
lmarena
leaderboard name
LMArena Webdev Image To Webdev
dimension
coding
metric
Arena rating
rank
60
sample size
2218
evaluated at
2026-11-10T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
1376.6307627212318
confidence upper
1406.9293576583145
Original result ↗

LMArena

1,232.618

source id
lmarena
leaderboard name
LMArena Vision Style Control English
dimension
multimodal
metric
Arena rating
rank
73
sample size
1840
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
1217.4976528589136
confidence upper
1247.7385482217676
Original result ↗

LMArena

1,201.748

source id
lmarena
leaderboard name
LMArena Vision Style Control Humor
dimension
multimodal
metric
Arena rating
rank
73
sample size
226
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
1160.9961831306337
confidence upper
1242.4999821538613
Original result ↗

LMArena

1,235.352

source id
lmarena
leaderboard name
LMArena Vision English
dimension
multimodal
metric
Arena rating
rank
78
sample size
1840
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
1220.2367427190388
confidence upper
1250.4674409735646
Original result ↗

LMArena

1,205.987

source id
lmarena
leaderboard name
LMArena Vision Humor
dimension
multimodal
metric
Arena rating
rank
78
sample size
226
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
1165.1440969428209
confidence upper
1246.829632043314
Original result ↗

LMArena

1,454.319

source id
lmarena
leaderboard name
LMArena Text Factuality Multi Turn
dimension
factuality
metric
Arena rating
rank
83
sample size
616
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
1433.3890883669335
confidence upper
1475.248311669986
Original result ↗

LMArena

1,195.662

source id
lmarena
leaderboard name
LMArena Vision Style Control Creative Writing Vision
dimension
multimodal
metric
Arena rating
rank
83
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
1166.0905260374764
confidence upper
1225.2344491020524
Original result ↗

LMArena

1,463.295

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Life And Physical And Social Science
dimension
factuality
metric
Arena rating
rank
84
sample size
655
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
1442.798901080028
confidence upper
1483.7910388260245
Original result ↗

LMArena

1,240.009

source id
lmarena
leaderboard name
LMArena Vision Style Control Diagram
dimension
multimodal
metric
Arena rating
rank
84
sample size
1428
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
1223.254710639093
confidence upper
1256.7633734813137
Original result ↗

LMArena

1,224.773

source id
lmarena
leaderboard name
LMArena Vision Style Control Ocr
dimension
multimodal
metric
Arena rating
rank
85
sample size
3783
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
1214.1981154439518
confidence upper
1235.348600929413
Original result ↗

LMArena

1,214.419

source id
lmarena
leaderboard name
LMArena Vision Overall
dimension
multimodal
metric
Arena rating
rank
85
sample size
5532
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
1205.1076108872328
confidence upper
1223.731368937403
Original result ↗

LMArena

1,222.717

source id
lmarena
leaderboard name
LMArena Vision Ocr
dimension
multimodal
metric
Arena rating
rank
86
sample size
3783
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
1212.0980923889974
confidence upper
1233.3367709046588
Original result ↗

LMArena

1,212.128

source id
lmarena
leaderboard name
LMArena Vision Style Control Overall
dimension
multimodal
metric
Arena rating
rank
86
sample size
5532
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
1202.8271310665173
confidence upper
1221.4281012468578
Original result ↗

LMArena

1,233.148

source id
lmarena
leaderboard name
LMArena Vision Diagram
dimension
multimodal
metric
Arena rating
rank
87
sample size
1428
evaluated at
2026-11-09T00:00:00.000Z
source model id
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
confidence lower
1216.3881440860187
confidence upper
1249.908191046301
Original result ↗

Provider specifications & access

1–1 / 1

nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 ↗

source model id
azure-huggingface/nvidia--nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
other
context length
1048576
architecture
input_modalities
  • text
  • image
  • video
output_modalities
  • text
capabilities

    Source specification observations

    1–1 / 1

    azureFoundry ↗

    field
    context_length
    value
    1048576
    normalized value
    1048576
    scope
    source-model
    source id
    azureFoundry
    confidence
    1

    Original sources

    1–5 / 5

    Hugging Face · nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 ↗

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model documentation ↗

    LMArena · Catalog ↗

    Microsoft Foundry · Catalog ↗

    Source links

    1–2 / 2

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace