Text models
Arena rating
THE MODEL, IN DETAIL / nvidia
nvidia-nemotron-3-super-120b-a12b
nvidia-nemotron-3-super-120b-a12bOpen weightsExplore published evaluation results, model specifications, and source-linked evidence for this exact model identity.
#175
Context window
Total token limit
Input price
USD / million input tokens
Output price
USD / million output tokens
Inference providers
Provider data not connected
Measured output speed
No model-level measurement
01 / PERFORMANCE
A clearer view of capability.
Read the score, understand the context, and explore where this model sits among its peers.
Performance fingerprint
Individual published accuracy scores · not a composite index
At least three published accuracy scores are needed for this view.
Performance meets price
Text models · same published source and version
GoogleAnthropicMetaxiaomi
In good company
Text models · Arena · official dataset
416 models in the source cohort. Showing selected nearby models. Evaluation settings can differ.
Evidence, by task.
Coverage is not a capability score.
0published results
0 evaluation sources
0 evaluation sources
ReasoningAwaiting evidence
CodingAwaiting evidence
MathematicsAwaiting evidence
VisionAwaiting evidence
AgenticAwaiting evidence
Long contextAwaiting evidence
Documented features, task evaluations, and preference rankings describe different things. Missing coverage does not imply a model cannot perform a task.
Explore our methodologyWhere people rank it
Published rankings for this exact model or configuration. Each source keeps its original metric.
02 / BENCHMARK EXPLORER
The numbers behind the model.
Original results, exact versions, and a direct path to the evidence behind every score.
Percentage-based evaluations will appear here when published.
0 percentage-based evaluations. Each benchmark measures a different task; compare results within the same evaluation and protocol.
03 / COST & VALUE
Know what your workload costs.
Explore token prices, see where the spend goes, and model a workload of your own.
Input—per million tokens
Output—per million tokens
Cache read—per million tokens
Cache write—per million tokens
Workload cost calculator
Change the numbers. See the trade-offs.
Cache-read pricing is not documented for this selection.
Token estimate only. Excludes cache writes, tools, and other provider fees. Actual token usage and provider limits vary.
Your estimated spend
1,000 requests · 11M tokens
Uncached input—
Cached input—
Output—
Per request—
Without cache discount—
Estimated cache savings—
Both input and output prices are needed to estimate this workload.
04 / INFERENCE NETWORK
One model. Different ways to run it.
Compare inference routes by price, context, quantization, and reported availability.
Provider routes have not been connected to this exact model identity.
Snapshot observed —. Speed and latency are the reported 30-minute median when available. This is a dated snapshot, not live monitoring.
Provider price comparison
USD per million tokens · input and output rates
No published measurements in this snapshot.
Reported availability
Provider availability over the selected observation window
No published measurements in this snapshot.
Output speed
Reported 30-minute p50 · tokens per second
No provider throughput measurements were returned in this snapshot.
Response latency
Reported 30-minute p50 · seconds
No provider latency measurements were returned in this snapshot.
Context by provider
Actual route limits can differ from the catalog maximum
No published measurements in this snapshot.
05 / CAPABILITIES & MODALITIES
What goes in. What comes out.
A map of documented interfaces and API features, separate from benchmark performance.
INPUT MODALITIES
Text
nvidia-nemotron-3-super-120b-a12bModel interface
OUTPUT MODALITIES
Text
Feature support
Listed catalog API parameters and documented pricing features
ReasoningNot documented
Tool callingNot documented
Tool choiceNot documented
Structured outputsNot documented
Response formatNot documented
Reasoning detailsNot documented
Seed controlNot documented
Stop sequencesNot documented
Prompt cachingNot documented
TemperatureNot documented
Room to work
Context capacity and completion limits
—total context tokens
Context window
Output tokens share the total context budget. The maximum completion length is a separate limit, and individual provider routes may have smaller limits.
- Catalog context
- Not documented
- Maximum output
- Not documented
- Top-provider context
- Not documented
06 / UNDER THE HOOD
The complete specification sheet.
Exact identities, model architecture, limits, and the defaults that shape a request.
Identity & architecture
- Developer
- nvidia
- Exact identity
nvidia-nemotron-3-super-120b-a12b- Subject
- Model Configuration
- Access
- Open weights
- License
- NVIDIA Open Model
- Parameters
- Not disclosed
- Tokenizer
- Not disclosed
- Instruction format
- Not disclosed
Reasoning & controls
- Reasoning
- Not documented
- Mandatory reasoning
- Not documented
- Reasoning by default
- Not documented
- Published configuration
- Not disclosed
- Supported reasoning efforts
- Not documented
- Default reasoning effort
- Not disclosed
- API parameters
- Not documented
- Provider moderation
- Not documented
- Quantization variants
- Not disclosed
Dates & limits
- Catalog added
- Not documented
- Knowledge cutoff
- Not disclosed
- Catalog expiration
- Not documented
- Specifications observed
- Not documented
- Providers observed
- Not documented
- Request limits
- Provider-specific / not supplied
- Canonical catalog ID
Not disclosed
API parameters & defaults
Availability is catalog-wide. Defaults can vary across providers.
API parameters have not been documented for this model.
07 / BUILD WITH THIS MODEL
From exploration to your first request.
Use the documented catalog identifier and keep your API key in an environment variable.
Make an API request
A public API identifier has not been connected to this exact model identity.
08 / PROVENANCE & HISTORY
Every number has a story.
Follow the source, check the observation date, and distinguish published results from model specifications.
The source register
Direct links to the underlying records
Text models ranking
Arena rating · source-reported ranking
Observed 15 Oct 2026The observation trail
Recorded events, in chronological order
Observation dates describe when data was captured. They do not represent newly run evaluations or continuous performance monitoring.
Published observation ledger
Historical evidence, with source and version preserved.
No published benchmark observations for this selection. Published preference rankings appear separately above.
09 / A FEW MORE DETAILS
Questions worth asking.
Quick answers, drawn from this model’s connected specifications.
How much does nvidia-nemotron-3-super-120b-a12b cost?
Input and output pricing are not fully documented for this model. Check the source register and provider routes for available information.
How much context can it handle?
A context limit has not been connected to this exact model identity.
Does it support tools and structured output?
Tool calling: not documented. Structured outputs: not documented. See the provider feature matrix for route-specific differences.
How should I interpret these benchmark results?
Read the benchmark name, exact version, metric, source, and model configuration together. Different evaluation settings can change the result. Preference ratings and source-defined composite indices remain separate from task accuracy.
Are these prices and provider measurements live?
This page uses dated source snapshots. Missing measurements are not estimated or treated as zero.
KEEP EXPLORING
More from nvidia.
Explore related identities from the same developer, or take them into a side-by-side comparison.