The LLM benchmark aggregator.

Nemotron 3.5 Super VL

NVIDIA · open weights

Strongest in Web research (#26 of 48, on 1 of its 2 boards), weakest in Agents (#188 of 289). Above par in 2 of 14 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and GPT-6 Astra and ahead of DeepSeek V3 and Gemini 3.5 Flash Lite.

§ 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.

Coding46.2−20.2#110/1761/6

Agentic coding45.8−21.2#108/1691/5

Reasoning46.5−18.3#123/1891/5

Reasoning44.4−22.3#90/1431/3

Professional45.4−17.7#142/1871/2

Document design32.6−34.5#41/471/1

Core abilities43.5−21.7#185/2252/4

Data analysis40.2−25.7#38/471/1

General intelligence43.9−24.9#154/2142/3

Agents46.1−19.8#188/2893/6

Web research50.4−13.3#26/481/2

Long-horizon work36.2−37.8#40/471/1

Knowledge work54.9−16.9#59/1982/2

Computer use34.6−33.3#73/801/2

§ 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 Nemotron 3.5 Super VL, left for the other.

GPT-4o Miniwon 9 · lost 0

GPT-4.1 Nanowon 9 · lost 0

NVIDIA Nemotron 3.5 Lightning 30B A3Bwon 14 · lost 0

Claude Haiku 4.5won 13 · lost 1

Gemma 4 31Bwon 13 · lost 1

NVIDIA Nemotron 3 Ultra 550B A55Bwon 13 · lost 1

Llama 4 Maverick Instructwon 7 · lost 2

GPT-5.4 Nanowon 6 · lost 3

Mistral Large 3won 6 · lost 3

Inklingwon 8 · lost 6

GPT-5.4 Miniwon 5 · lost 4

Gemini 3.5 Flash Litewon 5 · lost 4

DeepSeek V3won 5 · lost 4

GPT OSS 120Bwon 4 · lost 5

GPT-5 Miniwon 4 · lost 5

MiniMax M3won 6 · lost 8

Muse Spark Openwon 5 · lost 9

Gemini 3.1 Prowon 5 · lost 9

GPT-4.1 Miniwon 3 · lost 6

Inkling Smallwon 3 · lost 6

DeepSeek R1won 3 · lost 6

Claude Sonnet 4.5won 3 · lost 7

Kimi K2.5won 3 · lost 7

DeepSeek V3.2won 2 · lost 7

Gemini 2.5 Prowon 2 · lost 7

Gemini 3.5 Flashwon 2 · lost 7

Mistral Large 4won 3 · lost 11

Beam 1.0won 2 · lost 12

GLM-5.3 Flashwon 2 · lost 12

GPT-5won 1 · lost 8

Claude Sonnet 4won 1 · lost 9

Claude Haiku 5.5won 1 · lost 13

GPT-5.6 Lunawon 1 · lost 13

GPT-6 Lunawon 1 · lost 13

Claude Sonnet 4.6won 1 · lost 13

Step 5won 1 · lost 13

Qwen3.8 27Bwon 1 · lost 13

GLM-5.3won 1 · lost 13

Muse Spark 1.2won 1 · lost 13

DeepSeek V4 Flash Visionwon 1 · lost 13

GPT-5.6 Terrawon 1 · lost 13

Gemini 3.8 Flashwon 1 · lost 13

Claude Sonnet 5.5won 1 · lost 13

Qwen3.8 Maxwon 1 · lost 13

GPT-6 Solwon 1 · lost 13

GPT-5.6 Solwon 1 · lost 13

GPT-5.5won 1 · lost 13

Muse Spark 1.3won 1 · lost 13

GLM-5.2won 0 · lost 9

DeepSeek V4 Flashwon 0 · lost 9

DeepSeek V4 Prowon 0 · lost 9

Claude Opus 4.7won 0 · lost 9

GPT-5.4won 0 · lost 9

O3won 0 · lost 9

Qwen3.8 Flashwon 0 · lost 13

Claude Sonnet 5won 0 · lost 14

Claude Opus 5won 0 · lost 14

Grok 4.6won 0 · lost 14

Gemini 3.7 Flashwon 0 · lost 14

Mimo V2.6 Prowon 0 · lost 14

Claude Opus 4.8won 0 · lost 14

Kimi K3won 0 · lost 14

Grok 4.5won 0 · lost 14

DeepSeek V4.1 Flashwon 0 · lost 14

Grok 4.7won 0 · lost 14

Claude Opus 5.5won 0 · lost 14

Muse Wonderwon 0 · lost 14

Claude Fable 5.1won 0 · lost 14

Gemini 4 Argonwon 0 · lost 14

GPT-6.1 Solwon 0 · lost 14

GPT-6 Astrawon 0 · lost 14

Claude Fable 5won 0 · lost 14

§ 3 · Sources

Where the numbers come from

4 publications, 11 figures. Every one links to the page it was read from.

Artificial Analysis ↗1 measureread 2026-10-19

Artificial Analysis Intelligence Index 26

GDPval-AA ↗1 measureread 2026-10-19

GDPval-AA 1162

AA-Briefcase ↗1 measureread 2026-10-19

AA-Briefcase 999

LiveBench ↗8 measuresread 2026-10-19

LiveBench 51.5LiveBench · Agentic 15.8LiveBench · Reasoning 78.8LiveBench · Coding 65.5LiveBench · Browser Use 4LiveBench · Data Analysis 64.6LiveBench · Research 70.9LiveBench · Design 60.7

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=nemotron-3-5-super-vl)](https://publicai.io/model-index/m/nemotron-3-5-super-vl)