Skip to content
ModelCap

Nemotron 3 Super

Current board #57Arena #179Restricted licenseFree tier

NVIDIA·nvidia/nemotron-3-super-120b-a12b

Nemotron 3 Super is a language model published by NVIDIA. 3 OpenRouter endpoints are published in the latest snapshot. It accepts text input and returns text. The published context limit is 1M tokens. The catalogue declares support for reasoning, tool use, structured outputs.

ModelCap Index · Current board
52.7#57
Measured · 68% support · score interval 52.7–61.9
Market Gravity
53.8
Secondary market signal
Input
$0.085
per 1M tokens
Output
$0.40
per 1M tokens
Context
1M
tokens
Providers
3
endpoints
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
DigitalOceanCheapest$0.165$0.3581M—99.63%
DeepInfrabf16$0.085$0.40262Kbf1697.16%
Nebiusfp4$0.30$0.90262Kfp4100.0%

Reported evaluation leads (1)

Excluded from score

Structured rows reported in this exact model repository at the pinned revision below. They are useful research leads, but remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
Idavidrein/gpqa
diamond
—77.2727
Unpinned
not published
Reported
Quarantined

ModelCap Index · Current board

Methodology
52.7
Measured · 2 public benchmark observations across 2 boards
Current board
#57
Public rank basis
Measured (measured)
Index support
68.0% · strong
Index interval
52.7–61.9
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · nvidia/nvidia/nemotron-3-super-120b-a12b/fp8 · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8@7d7e5797b8a3c7abbab54033b6004e93e8b6bc91 (not the evaluation revision)
Direct benchmark observations
2
Breadth-adjusted BES point estimate
57.3
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
57.3
Evidence status
confirmed · 79% mass
General preference
57.1
Coding
57.8
Agents & tools
—
Reasoning
—
Evidence breadth
92%
Evidence coverage
68%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
40.3
Liquidity (providers × uptime)
85.1
Open reach (HF downloads)
—
Surface (context / tools / modalities)
85.0
Freshness
56.7
  • · OpenRouter popularity #30
  • · 3 live providers
  • · Catalogue: context 1000000, reasoning, tools
  • · First seen 2026-03-11

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
83.6
strong · 94% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
92.5
Deployability
99.8
Evaluation provenance
48.5

Missing: artifactReproducibility.base-lineage, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
53.8
OpenRouter weekly popularity
#30 of 298

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
Arena
Official rank
#179 of 385
Rating
1360.8
95% confidence interval
1354–1368
Votes
7K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
98%

Market Gravity breakdown

Usage55%
40.3

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
85.1

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
50.0

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
56.7

Time since first public availability, on a six-month half-life.

Specification

Context window
1M tokens
Max output
16K tokens
Inputs
Text
Outputs
Text
Tokenizer
Other
Cached input tokens
Not offered
First seen on OpenRouter
11 Mar 2026

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated

Weights & access

Restricted license. Downloadable weights use a model-specific or use-restricted license. Review the linked license before use, redistribution, or commercial deployment.

Access
Restricted license
Licence
nvidia-nemotron-open-model-license
Pinned revision
7d7e5797b8a3
Parameters
123.6B
Architecture
NemotronHForCausalLM
Model type
nemotron_h
Hugging Face downloads (30d)
193K
Downloads (all time)
2.4M
Likes
271
Repository
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
Repository updated
29 Apr 2026, 16:15 UTC