Mistral Small 4 vs Nemotron 3.5 Lightning
Nemotron 3.5 Lightning leads Mistral Small 4 on the Artificial Analysis Intelligence Index, 12.9 to 11.3, and Nemotron 3.5 Lightning costs 4.1x less per output token ($0.147 vs $0.60 per million). Updated October 22, 2026; 9 benchmarks have a result for both.
Mistral Small 4 or Nemotron 3.5 Lightning: which to pick
Only Nemotron 3.5 Lightning has a coding score, 22.6 on the Vibe Coding Index; Mistral Small 4 has none, so the two cannot be ranked on coding.
Pick Mistral Small 4 for work measured by SciCode or GPQA Diamond (Artificial Analysis run), where it leads.
- Shared results
- 9
- Mistral Small 4 only
- 6
- Nemotron 3.5 Lightning only
- 11
- Like-for-like categories
- 5 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
Only Nemotron 3.5 Lightning has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Nemotron 3.5 Lightning
Nemotron 3.5 Lightning leads, 12.9 against 11.3.
Same board, both measured
Agentic work
AA Agentic Index
Nemotron 3.5 Lightning
Nemotron 3.5 Lightning leads, 3.5 against 0.8.
Same board, both measured
Long documents
Listed context window
No call
Both take 262K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Nemotron 3.5 Lightning
Mistral Small 4 $0.0004, Nemotron 3.5 Lightning $0.0001 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
- Mistral Small 4 not benchmarked, Nemotron 3.5 Lightning 22.6 from 2 benchmarks.
- Widest category
- General, 10.7 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): Mistral Small 4 49.7% against Nemotron 3.5 Lightning 60.3%, 10.7 points apart on a 0 to 100 scale.
- Output price
- Mistral Small 4 $0.60 against Nemotron 3.5 Lightning $0.147 per million output tokens, 4.1x apart.
- Context window
- Both take 262K tokens.
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 | Mistral Small 4 | Bars | Nemotron 3.5 Lightning | Ties |
|---|---|---|---|---|
| Coding | 1 | 2 | 1 tie | |
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 1 | 1 | ||
| General | 0 | 1 | ||
| All shared boards | 2 | 6 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index12
| Benchmark | Mistral Small 4 | Nemotron 3.5 Lightning | Leader |
|---|---|---|---|
| AA Coding Index | 26.6 | 26.8 | Nemotron 3.5 Lightning |
| SWE-bench Verified (Vals AI) | Not measured | 52.8% | Only Nemotron 3.5 Lightning measured |
| Vibe Code Bench (Vals AI) | 0.0% | 0.0% | Tie |
| Code migration (Vals AI) | Not measured | 3.0% | Only Nemotron 3.5 Lightning measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Nemotron 3.5 Lightning measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 10.9% | Only Nemotron 3.5 Lightning measured |
| CyberBench (Vals AI) | Not measured | 29.5% | Only Nemotron 3.5 Lightning measured |
| SciCode | 38.8% | 32.1% | Mistral Small 4 |
| Terminal-Bench Hard (Artificial Analysis run) | 17.4% | Not measured | Only Mistral Small 4 measured |
| ALE-Bench | 497.6 | 769.2 | Nemotron 3.5 Lightning |
| Neither model has a result on the other 29 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mistral Small 4 | Nemotron 3.5 Lightning | Leader |
|---|---|---|---|
| AA Intelligence Index | 11.3 | 12.9 | Nemotron 3.5 Lightning |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mistral Small 4 | Nemotron 3.5 Lightning | Leader |
|---|---|---|---|
| AA Agentic Index | 0.8 | 3.5 | Nemotron 3.5 Lightning |
| Finance Agent (Vals AI) | Not measured | 18.5% | Only Nemotron 3.5 Lightning measured |
| Tax Agent Bench (Vals AI) | Not measured | 2.6% | Only Nemotron 3.5 Lightning measured |
| Legal Research Bench (Vals AI) | Not measured | 2.9% | Only Nemotron 3.5 Lightning measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 17.0% | Only Nemotron 3.5 Lightning measured |
| τ²-Bench Telecom | 41.2% | Not measured | Only Mistral Small 4 measured |
| Neither model has a result on the other 35 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Mistral Small 4 | Nemotron 3.5 Lightning | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 76.9% | 74.3% | Mistral Small 4 |
| Humanity's Last Exam (Artificial Analysis run) | 9.9% | 10.6% | Nemotron 3.5 Lightning |
| Kagi LLM Benchmark | 40.5% | Not measured | Only Mistral Small 4 measured |
| 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 | Mistral Small 4 | Nemotron 3.5 Lightning | 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 | Mistral Small 4 | Nemotron 3.5 Lightning | Leader |
|---|---|---|---|
| CorpFin (Vals AI) | Not measured | 54.2% | Only Nemotron 3.5 Lightning measured |
| Neither model has a result on the other 17 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Small 4 | Nemotron 3.5 Lightning | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mistral Small 4 | Nemotron 3.5 Lightning | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | Not measured | 4.3% | Only Nemotron 3.5 Lightning measured |
| IFBench | 48.2% | Not measured | Only Mistral Small 4 measured |
| Long context reasoning (AA-LCR) | 49.7% | 60.3% | Nemotron 3.5 Lightning |
| DTBench | 70.9% | Not measured | Only Mistral Small 4 measured |
| LMCA | 20.6% | Not measured | Only Mistral Small 4 measured |
| Neither model has a result on the other 41 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Small 4 | Nemotron 3.5 Lightning | 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 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 | Mistral Small 4 | NVIDIA Nemotron 3.5 Lightning |
|---|---|---|
| Maker | Mistral AI | NVIDIA |
| Weights | Open weights | Open weights |
| Released | March 16, 2026 | August 11, 2026 |
| Context window | 262K | 262K |
| Input $/Mtok | $0.15 | $0.0534 |
| Output $/Mtok | $0.60 | $0.147 |
| Coding index | Not benchmarked | 22.6 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | Not computable | $0.06 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Mistral Small 4 better than Nemotron 3.5 Lightning for coding?
Only Nemotron 3.5 Lightning has a coding score, 22.6 on the Vibe Coding Index; Mistral Small 4 has none, so the two cannot be ranked on coding. Pick Mistral Small 4 for work measured by SciCode or GPQA Diamond (Artificial Analysis run), where it leads.
Which is cheaper, Mistral Small 4 or Nemotron 3.5 Lightning?
Mistral Small 4 costs $0.15 per million input tokens and $0.60 per million output tokens; Nemotron 3.5 Lightning costs $0.0534 and $0.147. Cost per solved task is known for Nemotron 3.5 Lightning only.
Which has the bigger context window, Mistral Small 4 or Nemotron 3.5 Lightning?
Neither: both take 262K tokens.
How many benchmarks is the Mistral Small 4 vs Nemotron 3.5 Lightning comparison based on?
9 benchmarks have a result for both models as of October 22, 2026. Mistral Small 4's coding index rests on 1 independent benchmark and Nemotron 3.5 Lightning's on 2. Where only one model has a result, the page says so instead of naming a winner.