Nvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture. Provider-specific context limits vary, with the longest current route supporting up to 1M context. Thinking enabled.
Added Jun 4, 2026
Model weightsContext Window
1.0M
Max Output
65.5K
Avg output tokens (7d)
1.3K tokens
Input Price (Auto)
$0.50/1M
Output Price (Auto)
$2.50/1M
Cache Read (Auto)
$0.25/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
23.4
Coding Index
49.3
Agentic Index
21.7
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
3.0%
Better than 26% of models compared
AutomationBench-AA Tasks Completed
Fully completed workflows without guardrail violations
0.3%
Better than 7% of models compared
AA-Briefcase
Agentic knowledge work (Elo)
878 Elo
Better than 46% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
1091 Elo
Better than 55% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
5.0%
Better than 29% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
79.3%
Better than 87% of models compared
Reasoning
HLE
Humanity's Last Exam
28.4%
Better than 80% of models compared
IFBench
Instruction-following benchmark
81.4%
Better than 99% of models compared
CritPt
Research-level physics reasoning
3.1%
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
0.5%
Better than 39% of models compared
SciCode
Python programming for scientific computing
40.3%
Better than 30% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
22.6%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
29.7%
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
86.7%
Better than 82% of models compared
Terminal-Bench Hard (legacy)
Agentic coding and terminal use
36.4%
Better than 83% of models compared
T²-Bench Telecom (legacy)
Conversational AI agents in dual-control scenarios
83.3%
Better than 73% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
79.3%
Better than 87% of models compared
GDPval-AA (unversioned / legacy)
Economically valuable tasks
29.5%
Last updated Sep 13, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Related text models
Compare Nvidia Nemotron 3 Ultra 550B Thinking with similar models from the same provider or model family.
Nvidia Nemotron 3 Ultra 550B
nvidia/nemotron-3-ultra-550b-a55bNvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture. Provider-specific context limits vary, with the longest current route supporting up to 1M context.
Nvidia Nemotron 3.5 Lightning
nvidia/nemotron-3.5-lightningNvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. Thinking is disabled on this variant.
Nvidia Nemotron 3.5 Lightning Thinking
nvidia/nemotron-3.5-lightning:thinkingNvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. This variant enables its reasoning trace.
Nvidia Nemotron 3 Nano 30B
nvidia/nemotron-3-nano-30b-a3bNvidia's latest Nemotron 3 Nano model with 30B total parameters (3B active) using hybrid Mamba-Transformer MoE architecture. Features excellent throughput and strong reasoning capabilities.
Nvidia Nemotron 3 Super 120B
nvidia/nemotron-3-super-120b-a12bNvidia's Nemotron 3 Super 120B A12B model from the March 2026 Nemotron 3 release. It uses a hybrid Mamba-Transformer MoE architecture and targets agentic and coding workloads with a 262K context window here.
Nvidia Nemotron 3 Super 120B Thinking
nvidia/nemotron-3-super-120b-a12b:thinkingNvidia Nemotron 3 Super 120B with reasoning content enabled. Returns separate thinking content when requested.