Enter opens the highlighted result. Esc closes.

GPT-4.1 Nano vs Kimi K2 Thinking

Kimi K2 Thinking leads GPT-4.1 Nano on the Artificial Analysis Intelligence Index, 22.0 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; 23 benchmarks have a result for both.

Replace GPT-4.1 Nano Replace Kimi K2 Thinking
GPT-4.1 NanoOpenAI
Coding
No data
Overall
24.7
Output $/M
$0.40
0
Kimi K2 ThinkingMoonshot AI
Coding
No data
Overall
No data
Output $/M
$2.50
23
vs boards won of 23 shared

GPT-4.1 Nano or Kimi K2 Thinking: 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).

Model AGPT-4.1 NanoOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BKimi K2 ThinkingMoonshot AINot benchmarked1 independent benchmark$0.61 per solved task
Shared results
23
GPT-4.1 Nano only
48
Kimi K2 Thinking only
7
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.

At a glance

Coding index
GPT-4.1 Nano not benchmarked, Kimi K2 Thinking not benchmarked.
Widest category
Agentic work, 75.7 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: GPT-4.1 Nano 17.3% against Kimi K2 Thinking 93.0%, 75.7 points apart on a 0 to 100 scale.
Output price
GPT-4.1 Nano $0.40 against Kimi K2 Thinking $2.50 per million output tokens, 6.3x apart.
Context window
GPT-4.1 Nano takes 1.05M tokens, Kimi K2 Thinking 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.

Boards won, where both have a result
CategoryGPT-4.1 NanoBarsKimi K2 ThinkingTies
Coding04
Intelligence02
Agentic work01
Reasoning03
Math04
Knowledge06
Web design01
General02
All shared boards023
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for GPT-4.1 Nano and Kimi K2 Thinking
BenchmarkGPT-4.1 NanoKimi K2 ThinkingLeader
Aider polyglot8.9%Not measuredOnly GPT-4.1 Nano measured
SWE-bench VerifiedNot measured63.4%Only Kimi K2 Thinking measured
AA Coding Index11.1Not measuredOnly GPT-4.1 Nano measured
LiveCodeBench (Vals AI)42.7%63.1%Kimi K2 Thinking
SWE-bench Verified (Vals AI)Not measured60.2%Only Kimi K2 Thinking measured
LiveCodeBench (Artificial Analysis run)32.6%85.3%Kimi K2 Thinking
Terminal-Bench Hard (Artificial Analysis run)3.8%31.1%Kimi K2 Thinking
Terminal-BenchNot measured35.7%Only Kimi K2 Thinking measured
WeirdML19.0%42.8%Kimi K2 Thinking
ALE-BenchNot measured597.5Only Kimi K2 Thinking measured
LMArena Text: coding1306Not measuredOnly GPT-4.1 Nano measured
LMArena Text: software and IT1305Not measuredOnly GPT-4.1 Nano measured
Neither model has a result on the other 27 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-4.1 Nano and Kimi K2 Thinking
BenchmarkGPT-4.1 NanoKimi K2 ThinkingLeader
AA Intelligence Index7.822.0Kimi K2 Thinking
Epoch Capabilities Index129.5145.8Kimi K2 Thinking
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GPT-4.1 Nano and Kimi K2 Thinking
BenchmarkGPT-4.1 NanoKimi K2 ThinkingLeader
τ²-Bench Telecom17.3%93.0%Kimi K2 Thinking
METR time horizonsNot measured59.2%Only Kimi K2 Thinking measured
Berkeley Function Calling Leaderboard (BFCL)33.1%Not measuredOnly GPT-4.1 Nano measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
Reasoning benchmarks for GPT-4.1 Nano and Kimi K2 Thinking
BenchmarkGPT-4.1 NanoKimi K2 ThinkingLeader
GPQA Diamond50.8%78.5%Kimi K2 Thinking
MMMU Pro (Vals AI)55.0%Not measuredOnly GPT-4.1 Nano measured
GPQA Diamond (Artificial Analysis run)51.2%83.8%Kimi K2 Thinking
Humanity's Last Exam (Artificial Analysis run)3.8%23.8%Kimi K2 Thinking
GPQA Diamond (Epoch AI run)48.9%Not measuredOnly GPT-4.1 Nano measured
ARC-AGI0.0%Not measuredOnly GPT-4.1 Nano measured
ARC-AGI-20.0%Not measuredOnly GPT-4.1 Nano measured
Chess puzzles0.0%Not measuredOnly GPT-4.1 Nano measured
LMArena Text: hard prompts1286Not measuredOnly GPT-4.1 Nano measured
LMArena Text: expert1271Not measuredOnly GPT-4.1 Nano measured
LMArena Text: hard prompts in English1293Not measuredOnly GPT-4.1 Nano measured
Kagi LLM Benchmark33.3%Not measuredOnly GPT-4.1 Nano measured
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index04
Math benchmarks for GPT-4.1 Nano and Kimi K2 Thinking
BenchmarkGPT-4.1 NanoKimi K2 ThinkingLeader
AIME26.5%85.4%Kimi K2 Thinking
MATH 500 (Vals AI)80.2%Not measuredOnly GPT-4.1 Nano measured
MGSM (Vals AI)69.3%90.2%Kimi K2 Thinking
AA Math Index24.094.7Kimi K2 Thinking
AIME 2025 (Artificial Analysis run)24.0%94.7%Kimi K2 Thinking
OTIS Mock AIME28.9%Not measuredOnly GPT-4.1 Nano measured
MATH level 570.0%Not measuredOnly GPT-4.1 Nano measured
LMArena Text: math1274Not measuredOnly GPT-4.1 Nano measured
LMArena Text: mathematical work1274Not measuredOnly 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 index06
Knowledge benchmarks for GPT-4.1 Nano and Kimi K2 Thinking
BenchmarkGPT-4.1 NanoKimi K2 ThinkingLeader
MMLU Pro63.5%81.1%Kimi K2 Thinking
LegalBench (Vals AI)61.1%80.2%Kimi K2 Thinking
CaseLaw (Vals AI)Not measured65.7%Only Kimi K2 Thinking measured
CorpFin (Vals AI)42.1%60.6%Kimi K2 Thinking
TaxEval (Vals AI)60.8%71.7%Kimi K2 Thinking
MortgageTax (Vals AI)52.8%Not measuredOnly GPT-4.1 Nano measured
MedQA (Vals AI)68.2%92.6%Kimi K2 Thinking
MMLU Pro (Artificial Analysis run)65.7%84.8%Kimi K2 Thinking
SimpleQA Verified6.0%Not measuredOnly GPT-4.1 Nano measured
LMArena Text: science1297Not measuredOnly GPT-4.1 Nano measured
LMArena Text: medicine and healthcare1276Not measuredOnly GPT-4.1 Nano measured
LMArena Text: legal and government1300Not measuredOnly GPT-4.1 Nano measured
LMArena Text: business and finance1267Not measuredOnly GPT-4.1 Nano measured
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index01
Web design benchmarks for GPT-4.1 Nano and Kimi K2 Thinking
BenchmarkGPT-4.1 NanoKimi K2 ThinkingLeader
Design Arena: websites9721113Kimi K2 Thinking
Design Arena: UI components913Not measuredOnly GPT-4.1 Nano measured
Design Arena: game dev970Not measuredOnly GPT-4.1 Nano measured
Design Arena: data viz891Not measuredOnly GPT-4.1 Nano measured
Design Arena: 3D924Not measuredOnly GPT-4.1 Nano measured
Design Arena: all code categories962Not measuredOnly GPT-4.1 Nano measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
General benchmarks for GPT-4.1 Nano and Kimi K2 Thinking
BenchmarkGPT-4.1 NanoKimi K2 ThinkingLeader
IFBench32.0%68.1%Kimi K2 Thinking
Long context reasoning (AA-LCR)20.3%72.0%Kimi K2 Thinking
DTBench52.5%Not measuredOnly GPT-4.1 Nano measured
LMCA5.5%Not measuredOnly GPT-4.1 Nano measured
Fiction.LiveBench25.0%Not measuredOnly GPT-4.1 Nano measured
CL-benchNot measured17.6%Only Kimi K2 Thinking measured
LMArena Text1285Not measuredOnly GPT-4.1 Nano measured
LMArena Text: instruction following1266Not measuredOnly GPT-4.1 Nano measured
LMArena Text: creative writing1260Not measuredOnly GPT-4.1 Nano measured
LMArena Vision1063Not measuredOnly GPT-4.1 Nano measured
LMArena Text: English1303Not measuredOnly GPT-4.1 Nano measured
LMArena Text: non-English1260Not measuredOnly GPT-4.1 Nano measured
LMArena Text: Chinese1270Not measuredOnly GPT-4.1 Nano measured
LMArena Text: German1288Not measuredOnly GPT-4.1 Nano measured
LMArena Text: Japanese1198Not measuredOnly GPT-4.1 Nano measured
LMArena Text: Russian1261Not measuredOnly GPT-4.1 Nano measured
LMArena Text: multi-turn1277Not measuredOnly GPT-4.1 Nano measured
LMArena Text: longer queries1283Not measuredOnly GPT-4.1 Nano measured
LMArena Text: writing and language1261Not measuredOnly GPT-4.1 Nano measured
LMArena Text: entertainment and media1243Not measuredOnly GPT-4.1 Nano measured
LMArena Vision: English1101Not measuredOnly GPT-4.1 Nano measured
Neither model has a result on the other 25 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4.1 Nano and Kimi K2 Thinking
BenchmarkGPT-4.1 NanoKimi K2 ThinkingLeader
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$0.0003Fits in one request
Kimi K2 Thinking$0.0019Fits in one request

GPT-4.1 Nano costs less

Repository review

50K input + 3K output tokens

GPT-4.1 Nano$0.0062Fits in one request
Kimi K2 Thinking$0.037Fits in one request

GPT-4.1 Nano costs less

Agent loop

200K input + 10K output tokens

GPT-4.1 Nano$0.024Fits in one request
Kimi K2 Thinking$0.145Fits in one request

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.

Specifications of GPT-4.1 Nano and Kimi K2 Thinking
SpecificationOpenAI GPT-4.1 NanoMoonshotAI Kimi K2 Thinking
MakerOpenAIMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedApril 14, 2025November 6, 2025
Context window1.05M262K
Input $/Mtok$0.10$0.60
Output $/Mtok$0.40$2.50
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computable$0.61
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4.1 Nano better than Kimi K2 Thinking 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 Thinking?

GPT-4.1 Nano costs $0.10 per million input tokens and $0.40 per million output tokens; Kimi K2 Thinking costs $0.60 and $2.50. Cost per solved task is known for Kimi K2 Thinking only.

Which has the bigger context window, GPT-4.1 Nano or Kimi K2 Thinking?

GPT-4.1 Nano, with 1.05M tokens against 262K.

How many benchmarks is the GPT-4.1 Nano vs Kimi K2 Thinking comparison based on?

23 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 Thinking's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next