Nemotron 3.5 Lightning vs Extract
Updated October 22, 2026; no benchmark has tested both models yet.
- Coding
- 22.6
- Overall
- No data
- Output $/M
- $0.147
- Coding
- No data
- Overall
- No data
- Output $/M
- No data
Nemotron 3.5 Lightning or Extract: which to pick
Only Nemotron 3.5 Lightning has a coding score, 22.6 on the Vibe Coding Index; Extract has none, so the two cannot be ranked on coding.
Pick Extract for a larger context window (1M against 262K tokens).
No benchmark has tested both yet. Nemotron 3.5 Lightning has results on AA Coding Index, SWE-bench Verified (Vals AI) and Vibe Code Bench (Vals AI); Extract has none yet. Compare them on price and context instead.
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
Only Nemotron 3.5 Lightning has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Nemotron 3.5 Lightning has a AA Intelligence Index result, 12.9.
Directional only
Agentic work
AA Agentic Index
No call
Only Nemotron 3.5 Lightning has a AA Agentic Index result, 3.5.
Directional only
Long documents
Listed context window
Extract
Extract takes 1M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Extract
Nemotron 3.5 Lightning $0.0001, Extract $0.0000 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Nemotron 3.5 Lightning has the number, $0.06.
Directional only
At a glance
- Coding index
- Nemotron 3.5 Lightning 22.6 from 2 benchmarks, Extract not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- Nemotron 3.5 Lightning $0.147 against Extract Free per million output tokens.
- Context window
- Nemotron 3.5 Lightning takes 262K tokens, Extract 1M.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index9 boards measured
| Benchmark | Nemotron 3.5 Lightning | Extract | Leader |
|---|---|---|---|
| AA Coding Index | 26.8 | Not measured | Only Nemotron 3.5 Lightning measured |
| SWE-bench Verified (Vals AI) | 52.8% | Not measured | Only Nemotron 3.5 Lightning measured |
| Vibe Code Bench (Vals AI) | 0.0% | Not measured | Only Nemotron 3.5 Lightning measured |
| Code migration (Vals AI) | 3.0% | Not measured | Only Nemotron 3.5 Lightning measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Nemotron 3.5 Lightning measured |
| Terminal-Bench 2.1 (Vals AI) | 10.9% | Not measured | Only Nemotron 3.5 Lightning measured |
| CyberBench (Vals AI) | 29.5% | Not measured | Only Nemotron 3.5 Lightning measured |
| SciCode | 32.1% | Not measured | Only Nemotron 3.5 Lightning measured |
| ALE-Bench | 769.2 | Not measured | Only Nemotron 3.5 Lightning measured |
| Neither model has a result on the other 30 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Nemotron 3.5 Lightning | Extract | Leader |
|---|---|---|---|
| AA Intelligence Index | 12.9 | Not measured | Only Nemotron 3.5 Lightning measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | Nemotron 3.5 Lightning | Extract | Leader |
|---|---|---|---|
| AA Agentic Index | 3.5 | Not measured | Only Nemotron 3.5 Lightning measured |
| Finance Agent (Vals AI) | 18.5% | Not measured | Only Nemotron 3.5 Lightning measured |
| Tax Agent Bench (Vals AI) | 2.6% | Not measured | Only Nemotron 3.5 Lightning measured |
| Legal Research Bench (Vals AI) | 2.9% | Not measured | Only Nemotron 3.5 Lightning measured |
| Excel Modeling Benchmark (Vals AI) | 17.0% | Not measured | Only Nemotron 3.5 Lightning measured |
| Neither model has a result on the other 36 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Nemotron 3.5 Lightning | Extract | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 74.3% | Not measured | Only Nemotron 3.5 Lightning measured |
| Humanity's Last Exam (Artificial Analysis run) | 10.6% | Not measured | Only Nemotron 3.5 Lightning measured |
| Neither model has a result on the other 20 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Nemotron 3.5 Lightning | Extract | Leader |
|---|---|---|---|
| CorpFin (Vals AI) | 54.2% | Not measured | Only Nemotron 3.5 Lightning measured |
| Neither model has a result on the other 17 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Nemotron 3.5 Lightning | Extract | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | 4.3% | Not measured | Only Nemotron 3.5 Lightning measured |
| Long context reasoning (AA-LCR) | 60.3% | Not measured | Only Nemotron 3.5 Lightning measured |
| Neither model has a result on the other 44 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
Extract costs less
Repository review
50K input + 3K output tokens
Extract costs less
Agent loop
200K input + 10K output tokens
Extract 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 Lightning | ScaleDown Extract |
|---|---|---|
| Maker | NVIDIA | Scaledown |
| Weights | Open weights | No public weights listed |
| Released | August 11, 2026 | October 13, 2026 |
| Context window | 262K | 1M |
| Input $/Mtok | $0.0534 | $0.04 |
| Output $/Mtok | $0.147 | Free |
| Coding index | 22.6 | Not benchmarked |
| Independent measurements behind it | 2 | 0 |
| Cost per solved task | $0.06 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Nemotron 3.5 Lightning better than Extract for coding?
Only Nemotron 3.5 Lightning has a coding score, 22.6 on the Vibe Coding Index; Extract has none, so the two cannot be ranked on coding. Pick Extract for a larger context window (1M against 262K tokens).
Which is cheaper, Nemotron 3.5 Lightning or Extract?
Nemotron 3.5 Lightning costs $0.0534 per million input tokens and $0.147 per million output tokens; Extract costs $0.04 and Free. Cost per solved task is known for Nemotron 3.5 Lightning only.
Which has the bigger context window, Nemotron 3.5 Lightning or Extract?
Extract, with 1M tokens against 262K.
Has any benchmark tested both Nemotron 3.5 Lightning and Extract?
No benchmark has tested both yet. Nemotron 3.5 Lightning has results on AA Coding Index, SWE-bench Verified (Vals AI) and Vibe Code Bench (Vals AI); Extract has none yet. Compare them on price and context instead. Data as of October 22, 2026.