NVIDIA: Nemotron 3.5 Super VL

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video as …

nvidia/nemotron-3.5-super-vl-20261015

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video as input and returns text, and is built for long-running agents that combine visual understanding with reasoning and tool use.

It uses a hybrid Mamba-Transformer architecture with multi-token prediction and supports a 1M-token context. Typical uses include document intelligence, web research, coding validation, customer service, and video understanding. Reasoning is on by default and can be turned off or given a token budget.

Specifications & capabilities

Input
text, image, video
Output
text
Context window · tokens
1048576
Published model ID
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Description source ↗

Evaluations

21–23 / 23

OpenRouter Benchmarks

86.813%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · auto-routing
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
44
sample size
594
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
3
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:03:09.464Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
594
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8681253333333332
accuracy_std_dev
0.00965467639137749
cost_per_task_usd
0.021851893939393942
output_tokens_per_task
46276.513468013465
latency_seconds_per_task
524.4991397306397
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
132
benchmark_evaluation
true
openrouter_permaslug
nvidia/nemotron-3.5-super-vl-20261015
source model id
nvidia/nemotron-3.5-super-vl-20261015
Original result ↗

OpenRouter Benchmarks

72.889%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · auto-routing
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
52
sample size
150
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
3
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T12:32:08.127Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
150
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7288886666666667
accuracy_std_dev
0.017497738831695454
cost_per_task_usd
0.033088113333333335
output_tokens_per_task
14586.926666666666
latency_seconds_per_task
134.35410666666667
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
128
benchmark_evaluation
true
openrouter_permaslug
nvidia/nemotron-3.5-super-vl-20261015
source model id
nvidia/nemotron-3.5-super-vl-20261015
Original result ↗

Published prices

1–5 / 5

Provider specifications & access

1–2 / 2

nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 ↗

source model id
azure-huggingface/nvidia--nvidia-nemotron-3.5-super-vl-120b-a12b-bf16@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
other
context length
1048576
architecture
input_modalities
  • text
  • image
  • video
output_modalities
  • text
capabilities

    nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 ↗

    source model id
    azure-huggingface/nvidia--nvidia-nemotron-3.5-super-vl-120b-a12b-bf16@2
    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

      1–6 / 6

      azureFoundry ↗

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

      azureFoundry ↗

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

      openRouter ↗

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

      openRouter ↗

      field
      context_length
      value
      1000000
      normalized value
      1000000
      scope
      source-model
      source id
      openRouter
      confidence
      1

      openRouter ↗

      field
      max_output_tokens
      value
      235929
      normalized value
      235929
      scope
      source-model
      source id
      openRouter
      confidence
      1

      openRouter ↗

      field
      max_output_tokens
      value
      131072
      normalized value
      131072
      scope
      source-model
      source id
      openRouter
      confidence
      1

      Original sources

      1–9 / 9

      Hugging Face · nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 ↗

      Microsoft Foundry · Model page ↗

      Microsoft Foundry · Model page ↗

      OpenRouter · Model page ↗

      OpenRouter · Model page ↗

      Microsoft Foundry · Model documentation ↗

      Microsoft Foundry · Catalog ↗

      OpenRouter · Catalog ↗

      OpenRouter · Catalog ↗

      Source links

      1–5 / 5

      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