Nemotron 3.5 Super VL vs Sonar
Nemotron 3.5 Super VL leads Sonar on the Artificial Analysis Intelligence Index, 26.5 to 7.7, and Nemotron 3.5 Super VL costs 2.0x less per output token ($0.50 vs $1.00 per million). Updated October 22, 2026; 2 benchmarks have a result for both.
Nemotron 3.5 Super VL or Sonar: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Nemotron 3.5 Super VL for output tokens 2.0x cheaper ($0.50 vs $1.00 per million) and a larger context window (1.05M against 127K tokens).
- Shared results
- 2
- Nemotron 3.5 Super VL only
- 14
- Sonar only
- 3
- Like-for-like categories
- 2 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Nemotron 3.5 Super VL
Nemotron 3.5 Super VL leads, 26.5 against 7.7.
Same board, both measured
Web design
Design Arena: websites
No call
Only Nemotron 3.5 Super VL has a Design Arena: websites result, 1172.
Directional only
Long documents
Listed context window
Nemotron 3.5 Super VL
Nemotron 3.5 Super VL takes 1.05M tokens against 127K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Nemotron 3.5 Super VL
Nemotron 3.5 Super VL $0.0004, Sonar $0.0015 per turn.
List prices
At a glance
- Coding index
- Nemotron 3.5 Super VL not benchmarked, Sonar not benchmarked.
- Widest category
- Reasoning, 25.8 points apart on average over 1 shared benchmark.
- Widest single gap
- Humanity's Last Exam (Artificial Analysis run): Nemotron 3.5 Super VL 30.7% against Sonar 4.9%, 25.8 points apart on a 0 to 100 scale.
- Output price
- Nemotron 3.5 Super VL $0.50 against Sonar $1.00 per million output tokens, 2.0x apart.
- Context window
- Nemotron 3.5 Super VL takes 1.05M tokens, Sonar 127K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Nemotron 3.5 Super VL | Bars | Sonar | Ties |
|---|---|---|---|---|
| Intelligence | 1 | 0 | ||
| Reasoning | 1 | 0 | ||
| All shared boards | 2 | 0 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index3 boards, none shared
| Benchmark | Nemotron 3.5 Super VL | Sonar | Leader |
|---|---|---|---|
| LiveBench coding | 65.5% | Not measured | Only Nemotron 3.5 Super VL measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 29.5% | Only Sonar measured |
| SciCode | 47.8% | Not measured | Only Nemotron 3.5 Super VL measured |
| Neither model has a result on the other 36 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Nemotron 3.5 Super VL | Sonar | Leader |
|---|---|---|---|
| AA Intelligence Index | 26.5 | 7.7 | Nemotron 3.5 Super VL |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Nemotron 3.5 Super VL | Sonar | Leader |
|---|---|---|---|
| LiveBench research | 70.9% | Not measured | Only Nemotron 3.5 Super VL measured |
| LiveBench browser | 4.0% | Not measured | Only Nemotron 3.5 Super VL measured |
| LiveBench long agentic | 15.8% | Not measured | Only Nemotron 3.5 Super VL measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Nemotron 3.5 Super VL | Sonar | Leader |
|---|---|---|---|
| LiveBench reasoning | 78.8% | Not measured | Only Nemotron 3.5 Super VL measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 47.1% | Only Sonar measured |
| Humanity's Last Exam (Artificial Analysis run) | 30.7% | 4.9% | Nemotron 3.5 Super VL |
| Neither model has a result on the other 19 boards here | |||
MathNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Nemotron 3.5 Super VL | Sonar | Leader |
|---|---|---|---|
| Neither model has a result on 13 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Nemotron 3.5 Super VL | Sonar | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | Not measured | 68.9% | Only Sonar measured |
| Neither model has a result on the other 17 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Nemotron 3.5 Super VL | Sonar | Leader |
|---|---|---|---|
| Design Arena: websites | 1172 | Not measured | Only Nemotron 3.5 Super VL measured |
| Design Arena: UI components | 1153 | Not measured | Only Nemotron 3.5 Super VL measured |
| Design Arena: game dev | 1110 | Not measured | Only Nemotron 3.5 Super VL measured |
| Design Arena: 3D | 1127 | Not measured | Only Nemotron 3.5 Super VL measured |
| Design Arena: all code categories | 1155 | Not measured | Only Nemotron 3.5 Super VL measured |
| LiveBench design | 60.7% | Not measured | Only Nemotron 3.5 Super VL measured |
| Neither model has a result on the other 3 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Nemotron 3.5 Super VL | Sonar | Leader |
|---|---|---|---|
| LiveBench data analysis | 64.6% | Not measured | Only Nemotron 3.5 Super VL measured |
| Long context reasoning (AA-LCR) | 69.0% | Not measured | Only Nemotron 3.5 Super VL measured |
| Neither model has a result on the other 44 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Nemotron 3.5 Super VL | Sonar | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Nemotron 3.5 Super VL costs less
Repository review
50K input + 3K output tokens
Nemotron 3.5 Super VL costs less
Agent loop
200K input + 10K output tokens
Nemotron 3.5 Super VL costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | NVIDIA Nemotron 3.5 Super VL | Perplexity Sonar |
|---|---|---|
| Maker | NVIDIA | Perplexity |
| Weights | Open weights | No public weights listed |
| Released | October 15, 2026 | January 27, 2025 |
| Context window | 1.05M | 127K |
| Input $/Mtok | $0.15 | $1.00 |
| Output $/Mtok | $0.50 | $1.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Nemotron 3.5 Super VL better than Sonar for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Nemotron 3.5 Super VL for output tokens 2.0x cheaper ($0.50 vs $1.00 per million) and a larger context window (1.05M against 127K tokens).
Which is cheaper, Nemotron 3.5 Super VL or Sonar?
Nemotron 3.5 Super VL costs $0.15 per million input tokens and $0.50 per million output tokens; Sonar costs $1.00 and $1.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Nemotron 3.5 Super VL or Sonar?
Nemotron 3.5 Super VL, with 1.05M tokens against 127K.
How many benchmarks is the Nemotron 3.5 Super VL vs Sonar comparison based on?
2 benchmarks have a result for both models as of October 22, 2026. Nemotron 3.5 Super VL's coding index rests on 1 independent benchmark and Sonar's on 0. Where only one model has a result, the page says so instead of naming a winner.