GPT-4.1 Nano vs Kimi K2 0905
Kimi K2 0905 leads GPT-4.1 Nano on the Artificial Analysis Intelligence Index, 15.3 to 7.8, and GPT-4.1 Nano costs 6.3x less per output token ($0.40 vs $2.50 per million). Updated October 22, 2026; 16 benchmarks have a result for both.
GPT-4.1 Nano or Kimi K2 0905: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GPT-4.1 Nano for output tokens 6.3x cheaper ($0.40 vs $2.50 per million) and a larger context window (1.05M against 262K tokens).
- Shared results
- 16
- GPT-4.1 Nano only
- 55
- Kimi K2 0905 only
- 1
- Like-for-like categories
- 8 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
Kimi K2 0905
Kimi K2 0905 leads, 15.3 against 7.8.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only GPT-4.1 Nano has a GPQA Diamond result, 50.8%.
Directional only
Math
AIME
No call
Only GPT-4.1 Nano has a AIME result, 26.5%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-4.1 Nano has a MMLU Pro result, 63.5%.
Directional only
Web design
Design Arena: websites
Kimi K2 0905
Kimi K2 0905 leads, 1088 against 972.
Same board, both measured
Long documents
Listed context window
GPT-4.1 Nano
GPT-4.1 Nano takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-4.1 Nano
GPT-4.1 Nano $0.0003, Kimi K2 0905 $0.0019 per turn.
List prices
At a glance
- Coding index
- GPT-4.1 Nano not benchmarked, Kimi K2 0905 not benchmarked.
- Widest category
- Agentic work, 56.1 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: GPT-4.1 Nano 17.3% against Kimi K2 0905 73.4%, 56.1 points apart on a 0 to 100 scale.
- Output price
- GPT-4.1 Nano $0.40 against Kimi K2 0905 $2.50 per million output tokens, 6.3x apart.
- Context window
- GPT-4.1 Nano takes 1.05M tokens, Kimi K2 0905 262K.
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 | GPT-4.1 Nano | Bars | Kimi K2 0905 | Ties |
|---|---|---|---|---|
| Coding | 0 | 3 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 3 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 1 | ||
| Web design | 0 | 2 | ||
| General | 0 | 3 | ||
| All shared boards | 0 | 16 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
| Benchmark | GPT-4.1 Nano | Kimi K2 0905 | Leader |
|---|---|---|---|
| Aider polyglot | 8.9% | Not measured | Only GPT-4.1 Nano measured |
| AA Coding Index | 11.1 | Not measured | Only GPT-4.1 Nano measured |
| LiveCodeBench (Vals AI) | 42.7% | Not measured | Only GPT-4.1 Nano measured |
| LiveCodeBench (Artificial Analysis run) | 32.6% | 61.0% | Kimi K2 0905 |
| Terminal-Bench Hard (Artificial Analysis run) | 3.8% | 23.5% | Kimi K2 0905 |
| WeirdML | 19.0% | 36.7% | Kimi K2 0905 |
| ALE-Bench | Not measured | 267.1 | Only Kimi K2 0905 measured |
| LMArena Text: coding | 1306 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: software and IT | 1305 | Not measured | Only GPT-4.1 Nano measured |
| Neither model has a result on the other 30 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4.1 Nano | Kimi K2 0905 | Leader |
|---|---|---|---|
| AA Intelligence Index | 7.8 | 15.3 | Kimi K2 0905 |
| Epoch Capabilities Index | 129.5 | Not measured | Only GPT-4.1 Nano measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4.1 Nano | Kimi K2 0905 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 17.3% | 73.4% | Kimi K2 0905 |
| Berkeley Function Calling Leaderboard (BFCL) | 33.1% | Not measured | Only GPT-4.1 Nano measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | GPT-4.1 Nano | Kimi K2 0905 | Leader |
|---|---|---|---|
| GPQA Diamond | 50.8% | Not measured | Only GPT-4.1 Nano measured |
| MMMU Pro (Vals AI) | 55.0% | Not measured | Only GPT-4.1 Nano measured |
| GPQA Diamond (Artificial Analysis run) | 51.2% | 76.7% | Kimi K2 0905 |
| Humanity's Last Exam (Artificial Analysis run) | 3.8% | 6.4% | Kimi K2 0905 |
| GPQA Diamond (Epoch AI run) | 48.9% | Not measured | Only GPT-4.1 Nano measured |
| ARC-AGI | 0.0% | Not measured | Only GPT-4.1 Nano measured |
| ARC-AGI-2 | 0.0% | Not measured | Only GPT-4.1 Nano measured |
| Chess puzzles | 0.0% | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: hard prompts | 1286 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: expert | 1271 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: hard prompts in English | 1293 | Not measured | Only GPT-4.1 Nano measured |
| Kagi LLM Benchmark | 33.3% | 52.2% | Kimi K2 0905 |
| Neither model has a result on the other 10 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-4.1 Nano | Kimi K2 0905 | Leader |
|---|---|---|---|
| AIME | 26.5% | Not measured | Only GPT-4.1 Nano measured |
| MATH 500 (Vals AI) | 80.2% | Not measured | Only GPT-4.1 Nano measured |
| MGSM (Vals AI) | 69.3% | Not measured | Only GPT-4.1 Nano measured |
| AA Math Index | 24.0 | 57.3 | Kimi K2 0905 |
| AIME 2025 (Artificial Analysis run) | 24.0% | 57.3% | Kimi K2 0905 |
| OTIS Mock AIME | 28.9% | Not measured | Only GPT-4.1 Nano measured |
| MATH level 5 | 70.0% | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: math | 1274 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: mathematical work | 1274 | Not measured | Only GPT-4.1 Nano measured |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4.1 Nano | Kimi K2 0905 | Leader |
|---|---|---|---|
| MMLU Pro | 63.5% | Not measured | Only GPT-4.1 Nano measured |
| LegalBench (Vals AI) | 61.1% | Not measured | Only GPT-4.1 Nano measured |
| CorpFin (Vals AI) | 42.1% | Not measured | Only GPT-4.1 Nano measured |
| TaxEval (Vals AI) | 60.8% | Not measured | Only GPT-4.1 Nano measured |
| MortgageTax (Vals AI) | 52.8% | Not measured | Only GPT-4.1 Nano measured |
| MedQA (Vals AI) | 68.2% | Not measured | Only GPT-4.1 Nano measured |
| MMLU Pro (Artificial Analysis run) | 65.7% | 81.9% | Kimi K2 0905 |
| SimpleQA Verified | 6.0% | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: science | 1297 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: medicine and healthcare | 1276 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: legal and government | 1300 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: business and finance | 1267 | Not measured | Only GPT-4.1 Nano measured |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-4.1 Nano | Kimi K2 0905 | Leader |
|---|---|---|---|
| Design Arena: websites | 972 | 1088 | Kimi K2 0905 |
| Design Arena: UI components | 913 | Not measured | Only GPT-4.1 Nano measured |
| Design Arena: game dev | 970 | Not measured | Only GPT-4.1 Nano measured |
| Design Arena: data viz | 891 | Not measured | Only GPT-4.1 Nano measured |
| Design Arena: 3D | 924 | Not measured | Only GPT-4.1 Nano measured |
| Design Arena: all code categories | 962 | 1098 | Kimi K2 0905 |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | GPT-4.1 Nano | Kimi K2 0905 | Leader |
|---|---|---|---|
| IFBench | 32.0% | 41.7% | Kimi K2 0905 |
| Long context reasoning (AA-LCR) | 20.3% | 53.0% | Kimi K2 0905 |
| DTBench | 52.5% | Not measured | Only GPT-4.1 Nano measured |
| LMCA | 5.5% | Not measured | Only GPT-4.1 Nano measured |
| Fiction.LiveBench | 25.0% | 66.7% | Kimi K2 0905 |
| LMArena Text | 1285 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: instruction following | 1266 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: creative writing | 1260 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Vision | 1063 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: English | 1303 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: non-English | 1260 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: Chinese | 1270 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: German | 1288 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: Japanese | 1198 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: Russian | 1261 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: multi-turn | 1277 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: longer queries | 1283 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: writing and language | 1261 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Text: entertainment and media | 1243 | Not measured | Only GPT-4.1 Nano measured |
| LMArena Vision: English | 1101 | Not measured | Only GPT-4.1 Nano measured |
| Neither model has a result on the other 26 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4.1 Nano | Kimi K2 0905 | 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
GPT-4.1 Nano costs less
Repository review
50K input + 3K output tokens
GPT-4.1 Nano costs less
Agent loop
200K input + 10K output tokens
GPT-4.1 Nano 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 | OpenAI GPT-4.1 Nano | MoonshotAI Kimi K2 0905 |
|---|---|---|
| Maker | OpenAI | Moonshot AI |
| Weights | No public weights listed | Open weights |
| Released | April 14, 2025 | September 4, 2025 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $0.10 | $0.60 |
| Output $/Mtok | $0.40 | $2.50 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-4.1 Nano better than Kimi K2 0905 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4.1 Nano for output tokens 6.3x cheaper ($0.40 vs $2.50 per million) and a larger context window (1.05M against 262K tokens).
Which is cheaper, GPT-4.1 Nano or Kimi K2 0905?
GPT-4.1 Nano costs $0.10 per million input tokens and $0.40 per million output tokens; Kimi K2 0905 costs $0.60 and $2.50. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-4.1 Nano or Kimi K2 0905?
GPT-4.1 Nano, with 1.05M tokens against 262K.
How many benchmarks is the GPT-4.1 Nano vs Kimi K2 0905 comparison based on?
16 benchmarks have a result for both models as of October 22, 2026. GPT-4.1 Nano's coding index rests on 0 independent benchmarks and Kimi K2 0905's on 0. Where only one model has a result, the page says so instead of naming a winner.