Nemotron 3.5 Lightning vs Fugu Ultra
Nemotron 3.5 Lightning costs 204.1x less per output token than Fugu Ultra ($0.147 vs $30.00 per million). Updated October 23, 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
- $30.00
Nemotron 3.5 Lightning or Fugu Ultra: which to pick
Only Nemotron 3.5 Lightning has a coding score, 22.6 on the Vibe Coding Index; Fugu Ultra has none, so the two cannot be ranked on coding.
Pick Fugu Ultra 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); Fugu Ultra 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
Fugu Ultra
Fugu Ultra takes 1M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Nemotron 3.5 Lightning
Nemotron 3.5 Lightning $0.0001, Fugu Ultra $0.020 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, Fugu Ultra 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 Fugu Ultra $30.00 per million output tokens, 204.1x apart.
- Context window
- Nemotron 3.5 Lightning takes 262K tokens, Fugu Ultra 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 | Fugu Ultra | 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 34 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Nemotron 3.5 Lightning | Fugu Ultra | 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 | Fugu Ultra | 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 37 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Nemotron 3.5 Lightning | Fugu Ultra | 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 21 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Nemotron 3.5 Lightning | Fugu Ultra | Leader |
|---|---|---|---|
| CorpFin (Vals AI) | 54.2% | Not measured | Only Nemotron 3.5 Lightning measured |
| Neither model has a result on the other 19 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Nemotron 3.5 Lightning | Fugu Ultra | 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 46 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 Lightning costs less
Repository review
50K input + 3K output tokens
Nemotron 3.5 Lightning costs less
Agent loop
200K input + 10K output tokens
Nemotron 3.5 Lightning 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 | Sakana Fugu Ultra |
|---|---|---|
| Maker | NVIDIA | Sakana |
| Weights | Open weights | No public weights listed |
| Released | August 11, 2026 | June 24, 2026 |
| Context window | 262K | 1M |
| Input $/Mtok | $0.0534 | $5.00 |
| Output $/Mtok | $0.147 | $30.00 |
| 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 Fugu Ultra for coding?
Only Nemotron 3.5 Lightning has a coding score, 22.6 on the Vibe Coding Index; Fugu Ultra has none, so the two cannot be ranked on coding. Pick Fugu Ultra for a larger context window (1M against 262K tokens).
Which is cheaper, Nemotron 3.5 Lightning or Fugu Ultra?
Nemotron 3.5 Lightning costs $0.0534 per million input tokens and $0.147 per million output tokens; Fugu Ultra costs $5.00 and $30.00. Cost per solved task is known for Nemotron 3.5 Lightning only.
Which has the bigger context window, Nemotron 3.5 Lightning or Fugu Ultra?
Fugu Ultra, with 1M tokens against 262K.
Has any benchmark tested both Nemotron 3.5 Lightning and Fugu Ultra?
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); Fugu Ultra has none yet. Compare them on price and context instead. Data as of October 23, 2026.