Data as of October 20, 2026 · How the score is built
Released May 31, 2026N/A contextNVIDIA Cosmos3-Super model card
Cosmos3-Super
Decision readingCosmos3-Super is tracked, but not publicly ranked yet. The profile exposes 0 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released May 31, 2026 — see all recent releases
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not publishedNVIDIA Cosmos3-Super model card
- Context window
- N/A
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Open weights are available on Hugging Face under OpenMDW-1.1 for commercial and non-commercial use, with vLLM-Omni, SGLang and Diffusers serving instructions. The card limits text input to 4,096 tokens and states no overall context window. NVIDIA provides no first-party hosted token price for this checkpoint.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordNVIDIA Cosmos3-Super model card
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Cosmos3-Super, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
Cosmos3-Super is a open weight model with a N/A context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Open weights are available on Hugging Face under OpenMDW-1.1 for commercial and non-commercial use, with vLLM-Omni, SGLang and Diffusers serving instructions. The card limits text input to 4,096 tokens and states no overall context window. NVIDIA provides no first-party hosted token price for this checkpoint.
Official model-card snapshot for NVIDIA's Cosmos3-Super, released May 31, 2026 on Hugging Face and GitHub. The 64B-parameter Mixture-of-Transformers model pairs an autoregressive text tower with a diffusion generator for text, image, video, audio, and action workflows in physical AI. NVIDIA publishes world-model understanding and generation results, but no exact result maps to the current weighted LLM schema, so the model remains unranked.
Cosmos3-Super sits in the Cosmos 3 family with Cosmos3-Edge, Cosmos3-Nano. The profile has no source-displayable benchmark row yet.
Last updated October 20, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersQuestions
How does Cosmos3-Super perform overall in AI benchmarks?
Cosmos3-Super does not have any source-displayable benchmark rows yet, so this profile does not assign a public score or rank. Documented specifications remain visible, while score-led charts and claims stay unavailable until a published evaluation can be attached to the exact model.
Is Cosmos3-Super open source?
Cosmos3-Super is an open-weight model from NVIDIA. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Which sibling models are related to Cosmos3-Super?
Cosmos3-Super belongs to the Cosmos 3 family. Related tracked variants include Cosmos3-Edge, Cosmos3-Nano. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does Cosmos3-Super have full benchmark coverage on BenchLM?
No. Cosmos3-Super currently has 0 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Cosmos3-Super?
Cosmos3-Super has a reported context window of N/A in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.