NVIDIA Nemotron 3 Ultra 550B A55B
NVIDIA Nemotron 3 Ultra is NVIDIA’s Frontier reasoning model with 550 billion total and 55 billion active parameters on a hybrid Mamba-Transformer-MoE architecture with LatentMoE routing and MTP layers. The context window spans one million tokens, and reasoning is configurable. Native tool calls and agentic orchestration are supported; available as an Open Weights model under the NVIDIA Open Model License.
- Open Weights
- Frontier
- OpenRouter
- Text
- Instruction-Tuned
- Agentic Orchestrator
- Real-Time
Sovereign Risk: LOW Fully local inference possible without cloud connection. CLOUD Act is only relevant when using the API via NVIDIA infrastructure, not for local deployment of the publicly available weights.
Key metrics
Score · Latency · Cost · Quality
- Total Score Silver
- 72.53
- Routine
- 44.02
- Reasoning
- 28.51
- LLM Judge Avg
- 3.79 / 5
- 100 Coverage
- Avg Task Duration
- 15.99s
- Real-Time
- Token Rate
- 98.94tok/s
- Output Rate
- P95 Latency
- 46.01s
- Top 5 %
- Total Tokens
- 103100
- Output Volume
- Cost per 1K
- $0.0025
- USD / 1K Requests
- Benchmark Cost
- $0.26
- Total · 103100 tok
Benchmark modules
10 modules · weighted · vs. model median & top performer
NVIDIA Nemotron 3 Ultra 550B A55B
Best model
Ø All models
Code Quality
79.08
CLI Benchmark
95.33
Logical Reasoning
72.47
UX Writing
75.71
Documentation
73.13
Content Transform.
70.14
Cultural Intelligence
71.04
Synthesis Quality
29.17
Tool Execution
83.33
ToolUse Score
54.75
Benchmark Cost
$0.26
Token efficiency & latency
Consumption per module vs. model median
Token consumption per module
Performance profile
Key metrics – legend
Score
- Total Score
- Overall score derived from Routine and Reasoning scores. Basis for the fleet rank and tier assignment (Gold / Silver / Bronze).
- Routine
- Score for standard tasks: code generation, text transformation, structured outputs. Weighted by task complexity.
- Reasoning
- Score for analytical and logical tasks: multi-step problem solving, mathematical reasoning, structured argumentation.
- Rank
- Position in the fleet comparison, sorted by Total Score. Refers to the snapshot at the time of testing.
LLM Judge
- LLM Judge Ø
- Average quality rating by an independent judge model on a scale of 1–5.
- Coverage
- Share of tasks for which a judge rating is available. 100% means all responses were evaluated.
Latency & speed
- Avg. Task Duration
- Average time per task from the first to the last token of the response, measured across all benchmark tasks.
- Token Rate
- Output speed in tokens per second. Relevant for interactive applications and real-time streaming.
- P95 Latency
- 95th percentile of response times — shows outliers. Lower values mean fewer long wait times in edge cases.
Cost
- Cost per 1K
- API price per 1,000 output tokens in US dollars. Basis for cost calculation in production use.
- Benchmark Cost
- Total cost for the complete benchmark run of this model.