Nemotron 3.5 Lightning 30B A3B NVFP4

Nemotron 3.5 Lightning 30B A3B NVFP4 is a reasoning model from NVIDIA in the Nemotron 3.5 Lightning family. 18 benchmarks count toward its score, in 5 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.37.4 ±6.3
CoverageShare of the index weight with results.75%
SpeedOutput tokens per second.
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.1M
EloLMArena rating and rank.N/A

The index is a score out of 100. The ± range shows how much it can change.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
29.6
CodingCode writing and repair.
39.0
ReasoningLogic problems and puzzles.
40.3
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
40.8
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
50.9
MathMath problems.
N/A

Results

18 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
PinchBenchAgentic83.4%Kilo Code
Artificial Analysis Openness IndexKnowledge83.3%Artificial Analysis
Massive Multitask Language Understanding ProfessionalKnowledge81.6%49.1Yubo Wang et al.
Graduate-Level Google-Proof Q&AKnowledge75.6%48.0David Rein et al.
GPQA DiamondKnowledge75.6%48.0David Rein et al.
Artificial Analysis GPQA DiamondKnowledge74.3%44.7Artificial Analysis
Instruction Following BenchmarkInstruction72.9%50.9Benchmark authors
Software Engineering Benchmark VerifiedCoding52.8%39.9Carlos E. Jimenez et al.
Artificial Analysis Long Context ReasoningReasoning49.2%42.3Artificial Analysis
BrowseCompAgentic36.8%31.0OpenAI
Artificial Analysis SciCodeCoding32.1%37.4Artificial Analysis
Scientific Code BenchmarkCoding31.4%40.7Benchmark authors
Artificial Analysis Coding IndexCoding26.8%37.8Artificial Analysis
Artificial Analysis Omniscience AccuracyKnowledge14.4%31.7Artificial Analysis
Artificial Analysis Intelligence IndexKnowledge12.9%38.5Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge10.6%36.1Artificial Analysis
Humanity's Last Exam without toolsKnowledge10.5%37.7OpenAI
τ³-Bench Tool-Agent-User EvaluationAgentic9.5%5.0Sierra Research
GDPval-AA normalizedAgentic6.2%40.3Artificial Analysis
Artificial Analysis Agentic IndexAgentic6.1%42.2Artificial Analysis
Critical Physics TasksReasoning0.0%38.4Artificial Analysis

18 benchmarks count, from 19 of 21 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authors

More from NVIDIA

Nemotron 3 Ultra53.4Nemotron 3 Super 100B42.5Nemotron 3 Nano Omni 30B A3B36.9Nemotron 3 Nano 30B37.1Audio Flamingo 3 7BUnranked