Kimi K2 0905 vs Nemotron 3.5 Lightning
Kimi K2 0905 leads Nemotron 3.5 Lightning on the Artificial Analysis Intelligence Index, 15.3 to 12.9, and Nemotron 3.5 Lightning costs 17.0x less per output token ($0.147 vs $2.50 per million). Updated October 22, 2026; 5 benchmarks have a result for both.
Kimi K2 0905 or Nemotron 3.5 Lightning: which to pick
Only Nemotron 3.5 Lightning has a coding score, 22.6 on the Vibe Coding Index; Kimi K2 0905 has none, so the two cannot be ranked on coding.
Pick Kimi K2 0905 for work measured by AA Intelligence Index or GPQA Diamond (Artificial Analysis run), where it leads.
- Shared results
- 5
- Kimi K2 0905 only
- 12
- Nemotron 3.5 Lightning only
- 15
- Like-for-like categories
- 4 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
Kimi K2 0905
Kimi K2 0905 leads, 15.3 against 12.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Nemotron 3.5 Lightning has a AA Agentic Index result, 3.5.
Directional only
Web design
Design Arena: websites
No call
Only Kimi K2 0905 has a Design Arena: websites result, 1088.
Directional only
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
Kimi K2 0905 $0.0019, 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
- Kimi K2 0905 not benchmarked, Nemotron 3.5 Lightning 22.6 from 2 benchmarks.
- Widest category
- Coding, 16.7 points apart on average over 1 shared benchmark.
- Widest single gap
- ALE-Bench: Kimi K2 0905 267.1 against Nemotron 3.5 Lightning 769.2, 16.7 points apart on a 0 to 100 scale.
- Output price
- Kimi K2 0905 $2.50 against Nemotron 3.5 Lightning $0.147 per million output tokens, 17.0x 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 | Kimi K2 0905 | Bars | Nemotron 3.5 Lightning | Ties |
|---|---|---|---|---|
| Coding | 0 | 1 | ||
| Intelligence | 1 | 0 | ||
| Reasoning | 1 | 1 | ||
| General | 0 | 1 | ||
| All shared boards | 2 | 3 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
| Benchmark | Kimi K2 0905 | Nemotron 3.5 Lightning | Leader |
|---|---|---|---|
| AA Coding Index | Not measured | 26.8 | Only Nemotron 3.5 Lightning measured |
| SWE-bench Verified (Vals AI) | Not measured | 52.8% | Only Nemotron 3.5 Lightning measured |
| Vibe Code Bench (Vals AI) | Not measured | 0.0% | Only Nemotron 3.5 Lightning measured |
| 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 |
| LiveCodeBench (Artificial Analysis run) | 61.0% | Not measured | Only Kimi K2 0905 measured |
| SciCode | Not measured | 32.1% | Only Nemotron 3.5 Lightning measured |
| Terminal-Bench Hard (Artificial Analysis run) | 23.5% | Not measured | Only Kimi K2 0905 measured |
| WeirdML | 36.7% | Not measured | Only Kimi K2 0905 measured |
| ALE-Bench | 267.1 | 769.2 | Nemotron 3.5 Lightning |
| Neither model has a result on the other 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Kimi K2 0905 | Nemotron 3.5 Lightning | Leader |
|---|---|---|---|
| AA Intelligence Index | 15.3 | 12.9 | Kimi K2 0905 |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Kimi K2 0905 | Nemotron 3.5 Lightning | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 3.5 | Only Nemotron 3.5 Lightning measured |
| 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 | 73.4% | Not measured | Only Kimi K2 0905 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 | Kimi K2 0905 | Nemotron 3.5 Lightning | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 76.7% | 74.3% | Kimi K2 0905 |
| Humanity's Last Exam (Artificial Analysis run) | 6.4% | 10.6% | Nemotron 3.5 Lightning |
| Kagi LLM Benchmark | 52.2% | Not measured | Only Kimi K2 0905 measured |
| Neither model has a result on the other 19 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Kimi K2 0905 | Nemotron 3.5 Lightning | Leader |
|---|---|---|---|
| AA Math Index | 57.3 | Not measured | Only Kimi K2 0905 measured |
| AIME 2025 (Artificial Analysis run) | 57.3% | Not measured | Only Kimi K2 0905 measured |
| Neither model has a result on the other 11 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Kimi K2 0905 | Nemotron 3.5 Lightning | Leader |
|---|---|---|---|
| CorpFin (Vals AI) | Not measured | 54.2% | Only Nemotron 3.5 Lightning measured |
| MMLU Pro (Artificial Analysis run) | 81.9% | Not measured | Only Kimi K2 0905 measured |
| Neither model has a result on the other 16 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Kimi K2 0905 | Nemotron 3.5 Lightning | Leader |
|---|---|---|---|
| Design Arena: websites | 1088 | Not measured | Only Kimi K2 0905 measured |
| Design Arena: all code categories | 1098 | Not measured | Only Kimi K2 0905 measured |
| Neither model has a result on the other 7 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Kimi K2 0905 | Nemotron 3.5 Lightning | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | Not measured | 4.3% | Only Nemotron 3.5 Lightning measured |
| IFBench | 41.7% | Not measured | Only Kimi K2 0905 measured |
| Long context reasoning (AA-LCR) | 53.0% | 60.3% | Nemotron 3.5 Lightning |
| Fiction.LiveBench | 66.7% | Not measured | Only Kimi K2 0905 measured |
| Neither model has a result on the other 42 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Kimi K2 0905 | 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 | MoonshotAI Kimi K2 0905 | NVIDIA Nemotron 3.5 Lightning |
|---|---|---|
| Maker | Moonshot AI | NVIDIA |
| Weights | Open weights | Open weights |
| Released | September 4, 2025 | August 11, 2026 |
| Context window | 262K | 262K |
| Input $/Mtok | $0.60 | $0.0534 |
| Output $/Mtok | $2.50 | $0.147 |
| Coding index | Not benchmarked | 22.6 |
| Independent measurements behind it | 0 | 2 |
| Cost per solved task | Not computable | $0.06 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Kimi K2 0905 better than Nemotron 3.5 Lightning for coding?
Only Nemotron 3.5 Lightning has a coding score, 22.6 on the Vibe Coding Index; Kimi K2 0905 has none, so the two cannot be ranked on coding. Pick Kimi K2 0905 for work measured by AA Intelligence Index or GPQA Diamond (Artificial Analysis run), where it leads.
Which is cheaper, Kimi K2 0905 or Nemotron 3.5 Lightning?
Kimi K2 0905 costs $0.60 per million input tokens and $2.50 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, Kimi K2 0905 or Nemotron 3.5 Lightning?
Neither: both take 262K tokens.
How many benchmarks is the Kimi K2 0905 vs Nemotron 3.5 Lightning comparison based on?
5 benchmarks have a result for both models as of October 22, 2026. Kimi K2 0905's coding index rests on 0 independent benchmarks and Nemotron 3.5 Lightning's on 2. Where only one model has a result, the page says so instead of naming a winner.