NVIDIA
Nemotron 3 Ultra 550B A55B
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
nvidia/nemotron-3-ultra-550b-a55b
Context
1M
Output
128K
Released
2026-06-04
Knowledge cutoff
—
Types
Reasoning
Tool use
Structured output
Attachments
Open weights
Provider pricing
- Price
- $0.40 / $1.76
- Context
- 202.8K
- Status
- Stable
- Price
- $0.50 / $2.50
- Context
- 1M
- Status
- Stable
- Price
- $0.50 / $2.50
- Context
- 1M
- Status
- Stable
- Price
- $0.60 / $2.40
- Context
- 1M
- Status
- Stable
- Price
- $0.60 / $2.40
- Context
- 262.1K
- Status
- Stable
- Price
- $0.60 / $3.60
- Context
- 512.3K
- Status
- Stable
- Price
- $0.60 / $2.40
- Context
- 1M
- Status
- Stable
Benchmarks
SWE-Bench Verified
70.7 · resolved
SWE-Bench Multilingual
67.7 · resolve rate
Terminal-Bench
56.4 · success rate
GPQA
87 · accuracy
Humanity's Last Exam
26.7 · accuracy
Humanity's Last Exam
37.4 · accuracy
LiveCodeBench
89 · pass@1
MMLU-Pro
86.8 · accuracy
BrowseComp
44.4 · accuracy
IFBench
81.7 · accuracy
GDPval
46.7 · wins or ties
From the same lab
Nemotron 3.5 Super VL 120B A12B
nvidia/nemotron-3.5-super-vl-120b-a12b
Nemotron 3.5 Lightning 30B A3B
nvidia/nemotron-3.5-lightning
Nemotron 3.5 Content Safety
nvidia/nemotron-3.5-content-safety
Nemotron 3 Nano Omni 30B A3B Reasoning
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
Nemotron 3 Content Safety
nvidia/nemotron-3-content-safety
Llama Nemotron Rerank VL 1B v2
nvidia/llama-nemotron-rerank-vl-1b-v2
Nemotron Cascade 2 30B A3B
nvidia/nemotron-cascade-2-30b-a3b
Nemotron VoiceChat
nvidia/nemotron-voicechat