‹ PublicAI Index
The LLM benchmark aggregator.
Nemotron 3.5 Lightning
NVIDIA · 32B · open weights
Strongest in Knowledge work (#106 of 177), weakest in Coding (#164 of 164). Above par in 0 of 10 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and GPT-6 Astra and ahead of Trinity Large and Mercury 2.5.
§ 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.
Core abilities44.6−22.8#152/2041/3
General intelligence42.2−27.9#157/2041/3
Agents46.1−22#162/2672/5
Knowledge work44.9−28.7#106/1772/2
Professional37.6−24#162/1681/1
Medical32.9−33.9#135/1401/1
Finance37.6−25.3#136/1511/1
Legal37.3−29.8#139/1511/1
Coding37−32.1#164/1641/5
Agentic coding35.6−33.1#155/1571/4
§ 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 Nemotron 3.5 Lightning, left for the other.
§ 3 · Sources
Where the numbers come from
4 publications, 11 figures. Every one links to the page it was read from.
Artificial Analysis Intelligence Index 13
GDPval-AA 624
AA-Briefcase 505
Vals · Legal Research Bench 2.88%Vals · Harvey Legal Agent Benchmark 0%Vals · Finance Agent 18.5%Vals · CorpFin 54.23%Vals · MedScribe 4.27%Vals · SWE-bench Verified 52.8% (Mini-SWE-agent)Vals · Vibe Code Bench 0% (OpenHands)Vals · Code Migration 2.95%
Badge
[](https://publicai.io/model-index/m/nemotron-3-5-lightning)