Nemotron 3.5 Lightning (30B A3B)
Nemotron 3.5 Lightning (30B A3B) is NVIDIA's open-weight mixture-of-experts model with 30 billion total parameters (3B active), built for long-running agentic tasks. It delivers efficient agentic coding performance, ranking second on PinchBench, with a 262K token context window.
Key Specifications
Parameters
30.0B
Context
262.1K
Release Date
August 11, 2026
Average Score
45.3%
Timeline
Key dates in the model's history
Announcement
August 11, 2026
Last Update
August 27, 2026
Today
October 17, 2026
Technical Specifications
Parameters
30.0B
Training Tokens
-
Knowledge Cutoff
-
Family
-
Capabilities
MultimodalZeroEval
Pricing & Availability
Input (per 1M tokens)
$0.08
Output (per 1M tokens)
$0.20
Max Input Tokens
262.1K
Max Output Tokens
262.1K
Supported Features
Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning
Benchmark Results
Model performance metrics across various tests and benchmarks
Programming
Programming skills tests
SWE-Bench Verified
NeMo Evaluator; BF16 • Self-reported
Reasoning
Logical reasoning and analysis
GPQA
NeMo Gym / NeMo Evaluator; BF16; GPQA Diamond (no tools) • Self-reported
Other Tests
Specialized benchmarks
PinchBench
NeMo Gym / NeMo Evaluator; BF16 • Self-reported
MMLU-Pro
NeMo Gym / NeMo Evaluator; BF16 • Self-reported
IFBench
NeMo Gym / NeMo Evaluator; BF16; loose • Self-reported
AA-LCR
NeMo Gym / NeMo Evaluator; BF16 • Self-reported
BrowseComp
NeMo Gym / NeMo Evaluator; BF16 • Self-reported
Humanity's Last Exam
NeMo Gym / NeMo Evaluator; BF16; text-only, no tools • Self-reported
OmniScience
NeMo Gym / NeMo Evaluator; BF16; AA-Omniscience accuracy • Self-reported
SciCode
NeMo Gym / NeMo Evaluator; BF16 • Self-reported
SWE-bench Multilingual
NeMo Gym / NeMo Evaluator; BF16 • Self-reported
Tau3 Banking
NeMo Gym / NeMo Evaluator; BF16; τ³-bench (Banking) • Self-reported
Terminal-Bench 2.1
NeMo Evaluator; BF16 • Self-reported
License & Metadata
License
openmdw_license_v1_1
Announcement Date
August 11, 2026
Last Updated
August 27, 2026
Similar Models
All ModelsLlama 3.1 Nemotron 70B Instruct
NVIDIA
70.0B
Best score:0.8 (MMLU)
Released:Oct 2024
Nemotron 3 Nano (30B A3B)
NVIDIA
32.0B
Best score:0.8 (GPQA)
Released:Dec 2025
Price:$0.05/1M tokens
Llama-3.3 Nemotron Super 49B v1
NVIDIA
49.9B
Best score:0.7 (GPQA)
Released:Mar 2025
Nemotron 3 Super (120B A12B)
NVIDIA
120.0B
Best score:0.8 (GPQA)
Released:Mar 2026
Llama 3.1 Nemotron Ultra 253B v1
NVIDIA
253.0B
Best score:0.8 (GPQA)
Released:Apr 2025
GPT OSS 20B High
OpenAI
20.0B
Best score:0.7 (GPQA)
Released:Oct 2025
Price:$0.10/1M tokens
Llama 3.3 70B Instruct
Meta
70.0B
Best score:0.9 (HumanEval)
Released:Dec 2024
Price:$0.88/1M tokens
Phi 4 Reasoning Plus
Microsoft
14.0B
Best score:0.9 (HumanEval)
Released:Apr 2025
Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.