‹ PublicAI Index
The LLM benchmark aggregator.
NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)
NVIDIA · 32B · A3B · open weights
Strongest in Cybersecurity (#44 of 46), weakest in Agents (#289 of 289). Above par in 2 of 23 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5.5 and Claude Fable 5.1.
§ 1 · Profile
What it is good at
Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.
Human preference52.2−16.4#170/3501/1
Human preference52.2−16.4#170/3501/1
Coding32.4−34#176/1763/6
Agentic coding31.6−35.4#169/1693/5
Professional34.3−28.8#188/1882/2
Cybersecurity27−37#44/461/1
Document design26−41.3#48/481/1
Medical32.9−33.6#143/1491/1
Finance37.6−24.9#145/1611/1
Legal35.8−30.1#155/1641/1
Reasoning33.6−31.3#189/1902/5
Reasoning31.8−34.9#144/1441/3
Mathematics32.9−31.2#149/1501/2
Core abilities29.8−35.4#225/2253/4
Data analysis26−40.1#48/481/1
Instruction following26.8−47#60/621/1
Language26−40.6#62/621/1
General intelligence35−33.8#205/2142/3
Agents36.6−29.3#289/2893/6
Web research30−32.6#48/491/2
Long-horizon work31.8−42.2#48/481/1
Computer use33.2−34.5#79/811/2
Knowledge work43.6−28.2#125/1982/2
§ 2 · Head to head
What it beats, and what beats it
The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4), left for the other.
§ 3 · Sources
Where the numbers come from
7 publications, 27 figures. Every one links to the page it was read from.
LMArena Text 1353
Artificial Analysis Intelligence Index 13
GDPval-AA 639
AA-Briefcase 506
LiveBench 28.7LiveBench · Agentic 8.3LiveBench · Reasoning 42.9LiveBench · Coding 22.6LiveBench · Browser Use 0LiveBench · Data Analysis 43.1LiveBench · Research 40LiveBench · Design 43.9
LiveBench 1.0 44.5LiveBench 1.0 · Reasoning 42.9LiveBench 1.0 · Coding 45.8LiveBench 1.0 · Agentic Coding 19.9LiveBench 1.0 · Mathematics 66.5LiveBench 1.0 · Data Analysis 43.1LiveBench 1.0 · Language 38.3LiveBench 1.0 · Instruction Following 54.9
Vals · Legal Research Bench 2.88%Vals · Finance Agent 18.5%Vals · CorpFin 54.23%Vals · MedScribe 4.27%Vals · CyberBench 29.46%Vals · SWE-bench Verified 52.8% (Mini-SWE-agent)Vals · Code Migration 2.95%
Badge
[](https://publicai.io/model-index/m/nvidia-nemotron-3-5-lightning-30b-a3b-nvfp4)