‹ PublicAI Index
The LLM benchmark aggregator.
Smaug Nemotron 3.5
NVIDIA
Strongest in Data analysis (#24 of 31), weakest in Agents (#285 of 298). Above par in 0 of 13 scopes. Among the models it meets almost everywhere, it finishes behind GPT-6 Astra and Claude Fable 5.2 and ahead of Inkling and Nemotron 3.5 Super VL.
§ 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.
Coding43.2−23#141/1791/6
Agentic coding42.5−24.4#139/1731/5
Professional44.9−17.5#153/1941/2
Document design30.7−38#27/311/1
Reasoning41.3−24.1#165/1951/5
Reasoning36−33#139/1471/3
Core abilities40.7−24.6#183/1991/4
Data analysis39.2−26#24/311/1
General intelligence38.7−30.7#161/1781/3
Agents40.2−26.2#285/2981/6
Long-horizon work35.7−38.3#29/311/1
Web research40.8−23.1#30/351/2
Computer use38.3−29.8#58/681/2
§ 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 Smaug Nemotron 3.5, left for the other.
§ 3 · Sources
Where the numbers come from
1 publication, 8 figures. Every one links to the page it was read from.
LiveBench 47LiveBench · Agentic 11.3LiveBench · Reasoning 75.1LiveBench · Coding 51.5LiveBench · Browser Use 25.6LiveBench · Data Analysis 65.1LiveBench · Research 66.8LiveBench · Design 60.6
Badge
[](https://publicai.io/model-index/m/smaug-nemotron-3-5)