Nemotron 3.5 Super VL
Nemotron 3.5 Super VL is capable in factuality; and behind the leaders in long context, reasoning, coding, and agentic tasks. Too few results yet to rate safety, math, multimodal tasks, multilingual tasks, or instruction following.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Safety, Math, Multimodal, Multilingual or Instruction Following.
Price
$0.15input$0.50outputper million tokens
From Artificial Analysis · 3 providers tracked · All prices
Evidence
53results on45benchmarks
- 9 independently verified
- 14 aggregator
- 30 cross-referenced
From 7 sources · latest Nov 21, 2026 · How verification works
API features
Tool callingStructured outputsReasoning
As listed by OpenRouter
Nemotron 3.5 Super VL benchmark results
53 results on 45 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
25.0% behind the leader2 of 4 ranked benchmarks measured
- AA-Omniscience · Non-hallucination64.15Oct 16, 2026omniscienceNonHallucination
- AA-Omniscience · Accuracy23.28Oct 16, 2026omniscienceAccuracy
32.0% behind the leader2 of 3 ranked benchmarks measured
- 62.10Nov 20, 2026
- 69.00Nov 21, 2026
32.4% behind the leader3 of 6 ranked benchmarks measured
- Humanity's Last Exam30.72Nov 21, 2026aa_hle
- 10.57Nov 21, 2026
- 1.53Oct 22, 2026
34.1% behind the leader4 of 10 ranked benchmarks measured
- 71.10Nov 20, 2026
- SciCode47.80Nov 21, 2026aa_scicode
- 67.70Nov 20, 2026
- Terminal-Bench 2.160.70Nov 20, 2026Terminal Bench v2.1
42.1% behind the leader4 of 7 ranked benchmarks measured
- 78.90Nov 20, 2026
- 67.70Nov 20, 2026
- 33.12Oct 16, 2026
- Terminal-Bench 4.00.00Nov 21, 2026
0 of 6 ranked benchmarks measured
- 67.40Oct 15, 2026
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- 2.00Oct 22, 2026
- 20.17Oct 22, 2026
- 22.67Oct 22, 2026
- AA Intelligence14.00Oct 16, 2026Artificial Analysis Intelligence Index
- 56.60Oct 15, 2026
- GDP (Surge AI)8.00Nov 21, 2026gdp-pdf
Show 29 more resultsHide 29 results
- AA Intelligence26.49Oct 16, 2026aa_intelligence_index
- -4.22Oct 16, 2026
- ARC-AGI-122.70Nov 20, 2026ARC-AGI v1
- AutomationBench-AA v1.0.614.80Nov 20, 2026
- BVB52.10Nov 20, 2026
- Chartography original9.70Nov 20, 2026
- ComplexConstraints v1.130.10Nov 20, 2026
- Covert misbehavior (Internal) ↓43.40Nov 20, 2026
- CritPt v2 Full36.90Nov 20, 2026
- CritPt v2 Hard13.50Nov 21, 2026
- DeepSearchQA (F1)77.70Nov 20, 2026DeepSearchQA
- DeepSWE 1.124.70Nov 20, 2026DeepSWE v1.1
- GDP (Surge AI)8.00Nov 20, 2026GDP.pdf
- GDPval-AA 2.11162.00Nov 20, 2026GDPVal-AA v2.1
- 63.30Nov 20, 2026
- HLE-Diamond8.80Nov 21, 2026
- HLE-Diamond8.80Nov 20, 2026
- 36.50Nov 20, 2026
- Misbehavior (Internal) ↓52.80Nov 20, 2026
- 72.30Nov 20, 2026
- MRCR v2 8-needle 256K–512K5.70Nov 20, 2026
- OmniDocBench v1.677.90Nov 20, 2026
- ScreenSpot Pro original43.50Nov 20, 2026
- StrongREJECT (none)99.40Nov 20, 2026
- SWEBench Pro v2 (Hard)44.10Nov 20, 2026
- Terminal-Bench 4.00.00Nov 20, 2026Terminal Bench v4.0
- Terminal-Bench-Science 0.10.00Nov 21, 2026
- 41.00Nov 20, 2026
- ZeroBench (main) original11.00Nov 20, 2026
Nemotron 3.5 Super VL: common questions
Who makes Nemotron 3.5 Super VL?
Nemotron 3.5 Super VL is made by NVIDIA.
When was Nemotron 3.5 Super VL released?
Nemotron 3.5 Super VL was released on Oct 15, 2026, according to Artificial Analysis.
What is Nemotron 3.5 Super VL good at?
Nemotron 3.5 Super VL is capable in factuality; and behind the leaders in long context, reasoning, coding, and agentic tasks. Too few results yet to rate safety, math, multimodal tasks, multilingual tasks, or instruction following.
How much does Nemotron 3.5 Super VL cost?
Nemotron 3.5 Super VL costs $0.15 per million input tokens and $0.50 per million output tokens, according to Artificial Analysis. We track its price at 3 providers. At a mix of three input tokens to one output token, it is cheaper than 76% of the 337 priced models we track.
How many benchmarks has Nemotron 3.5 Super VL been tested on?
We track 53 results for Nemotron 3.5 Super VL on 45 benchmarks from 7 sources, 9 of them independently verified. The latest was recorded on Nov 21, 2026.
Which API features does Nemotron 3.5 Super VL support?
OpenRouter lists tool calling, structured outputs, and reasoning for Nemotron 3.5 Super VL.
About this record
Where Nemotron 3.5 Super VL's numbers come from, and every name it appears under.
- Tracked since
- Oct 16, 2026
- Newest source mention
- Oct 22, 2026
Where the results come from
Verification: 53 scores · 9 independently verified · 14 aggregator-attributed · 30 vendor cross-reference. How these tiers are assigned
From 7 sources on 4 sites. Hugging Face supplies 30 of them; the 9 independently verified results come from 3 sites. Bars are coloured by trust tier.
- huggingface.co30
- artificialanalysis.ai15
- arcprize.org6
- 99franklin.github.io2
Also known as
How our sources name Nemotron 3.5 Super VL at each reasoning setting.
| Setting | Short form |
|---|---|
| medium | nemotron 3.5 super vl (medium) |
| high | nemotron 3.5 super vl (high) |