Enter opens the highlighted result. Esc closes.

GPT-5.4 Nano vs Kimi K2.5

GPT-5.4 Nano leads Kimi K2.5 on coding, 44.8 to 38.6 on the Vibe Coding Index, and GPT-5.4 Nano costs 2.3x less per output token ($1.25 vs $2.85 per million). Updated October 22, 2026; 71 benchmarks have a result for both.

Replace GPT-5.4 Nano Replace Kimi K2.5
GPT-5.4 NanoOpenAI
Coding
44.8
Overall
45.7
Output $/M
$1.25
12
Kimi K2.5Moonshot AI
Coding
38.6
Overall
44.8
Output $/M
$2.85
59
vs boards won of 71 shared

GPT-5.4 Nano or Kimi K2.5: which to pick

Pick GPT-5.4 Nano for coding: it scores 44.8 on the Vibe Coding Index against 38.6 for Kimi K2.5, though on 2 benchmarks against 3.

Pick Kimi K2.5 for work measured by SWE-bench Verified (Vals AI) or Terminal-Bench 2.1 (Vals AI), where it leads.

Model AGPT-5.4 NanoOpenAI44.8/1002 independent benchmarks$0.14 per solved taskModel BKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved task
Shared results
71
GPT-5.4 Nano only
14
Kimi K2.5 only
28
Like-for-like categories
7 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-5.4 Nano 44.8 from 2 benchmarks, Kimi K2.5 38.6 from 3 benchmarks.
Widest category
General, 12.9 points apart on average over 28 shared benchmarks.
Widest single gap
Kagi LLM Benchmark: GPT-5.4 Nano 39.7% against Kimi K2.5 78.5%, 38.8 points apart on a 0 to 100 scale.
Output price
GPT-5.4 Nano $1.25 against Kimi K2.5 $2.85 per million output tokens, 2.3x apart.
Context window
GPT-5.4 Nano takes 400K tokens, Kimi K2.5 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-5.4 NanoBarsKimi K2.5Ties
Coding74
Intelligence02
Agentic work22
Reasoning012
Math03
Knowledge110
General226
All shared boards1259
CodingLike-for-likeSix of these boards feed the Vibe Coding Index74
Coding benchmarks for GPT-5.4 Nano and Kimi K2.5
BenchmarkGPT-5.4 NanoKimi K2.5Leader
SWE-bench VerifiedNot measured70.8%Only Kimi K2.5 measured
SWE-bench MultilingualNot measured67.3%Only Kimi K2.5 measured
LMArena WebDevNot measured1437Only Kimi K2.5 measured
AA Coding Index56.146.8GPT-5.4 Nano
LiveCodeBench (Vals AI)84.0%83.9%GPT-5.4 Nano
SWE-bench Verified (Vals AI)69.8%70.0%Kimi K2.5
Vibe Code Bench (Vals AI)26.1%17.5%GPT-5.4 Nano
Code migration (Vals AI)14.5%7.0%GPT-5.4 Nano
Terminal-Bench 2.1 (Vals AI)41.6%42.0%Kimi K2.5
SciCode47.2%Not measuredOnly GPT-5.4 Nano measured
Terminal-Bench Hard (Artificial Analysis run)42.4%34.8%GPT-5.4 Nano
Terminal-BenchNot measured43.2%Only Kimi K2.5 measured
WeirdML49.2%45.6%GPT-5.4 Nano
ALE-Bench1004.5821.6GPT-5.4 Nano
LMArena Text: coding14041483Kimi K2.5
LMArena Text: software and IT14021471Kimi K2.5
LMArena WebDev: ReactNot measured1429Only Kimi K2.5 measured
LMArena WebDev: HTMLNot measured1426Only Kimi K2.5 measured
LMArena WebDev: from an imageNot measured1439Only Kimi K2.5 measured
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-5.4 Nano and Kimi K2.5
BenchmarkGPT-5.4 NanoKimi K2.5Leader
AA Intelligence Index20.723.5Kimi K2.5
Epoch Capabilities Index146.0148.1Kimi K2.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index22
Agentic work benchmarks for GPT-5.4 Nano and Kimi K2.5
BenchmarkGPT-5.4 NanoKimi K2.5Leader
AA Agentic Index16.0Not measuredOnly GPT-5.4 Nano measured
Design Arena: agents building web appsNot measured1136Only Kimi K2.5 measured
Design Arena: agents building full-stack appsNot measured1114Only Kimi K2.5 measured
Design Arena: agents building mobile appsNot measured1147Only Kimi K2.5 measured
Design Arena: agents building Android appsNot measured1118Only Kimi K2.5 measured
Design Arena: agents building Godot gamesNot measured1219Only Kimi K2.5 measured
Finance Agent (Vals AI)38.2%35.8%GPT-5.4 Nano
Tax Agent Bench (Vals AI)5.0%Not measuredOnly GPT-5.4 Nano measured
Legal Research Bench (Vals AI)6.3%15.9%Kimi K2.5
Excel Modeling Benchmark (Vals AI)44.8%28.5%GPT-5.4 Nano
τ²-Bench Telecom76.0%95.9%Kimi K2.5
OSWorldNot measured63.3%Only Kimi K2.5 measured
Vending-Bench 2Not measured$1,198Only Kimi K2.5 measured
Neither model has a result on the other 28 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index012
Reasoning benchmarks for GPT-5.4 Nano and Kimi K2.5
BenchmarkGPT-5.4 NanoKimi K2.5Leader
GPQA Diamond77.5%84.1%Kimi K2.5
MMMU Pro (Vals AI)73.6%84.3%Kimi K2.5
GPQA Diamond (Artificial Analysis run)81.7%87.9%Kimi K2.5
Humanity's Last Exam (Artificial Analysis run)28.3%30.7%Kimi K2.5
GPQA Diamond (Epoch AI run)78.5%Not measuredOnly GPT-5.4 Nano measured
ARC-AGI51.5%65.3%Kimi K2.5
ARC-AGI-25.7%11.8%Kimi K2.5
SimpleBenchNot measured46.8%Only Kimi K2.5 measured
Chess puzzles45.0%Not measuredOnly GPT-5.4 Nano measured
Mystery game puzzles9.0%Not measuredOnly GPT-5.4 Nano measured
LMArena Text: hard prompts13811453Kimi K2.5
LMArena Text: expert13961466Kimi K2.5
LMArena Text: hard prompts in English13871460Kimi K2.5
LMArena Vision: diagrams12101282Kimi K2.5
LMArena Vision: homework12251297Kimi K2.5
Kagi LLM Benchmark39.7%78.5%Kimi K2.5
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for GPT-5.4 Nano and Kimi K2.5
BenchmarkGPT-5.4 NanoKimi K2.5Leader
AIME88.8%95.6%Kimi K2.5
OTIS Mock AIME87.8%Not measuredOnly GPT-5.4 Nano measured
FrontierMath, tiers 1 to 344.9%Not measuredOnly GPT-5.4 Nano measured
FrontierMath, tier 412.2%Not measuredOnly GPT-5.4 Nano measured
ProofBench5.0%Not measuredOnly GPT-5.4 Nano measured
LMArena Text: math14051470Kimi K2.5
LMArena Text: mathematical work14091473Kimi K2.5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index110
Knowledge benchmarks for GPT-5.4 Nano and Kimi K2.5
BenchmarkGPT-5.4 NanoKimi K2.5Leader
MMLU Pro77.2%85.9%Kimi K2.5
LegalBench (Vals AI)77.9%Not measuredOnly GPT-5.4 Nano measured
CaseLaw (Vals AI)51.9%58.7%Kimi K2.5
CorpFin (Vals AI)61.2%68.3%Kimi K2.5
TaxEval (Vals AI)67.4%74.2%Kimi K2.5
MortgageTax (Vals AI)59.1%66.5%Kimi K2.5
MedQA (Vals AI)Not measured94.4%Only Kimi K2.5 measured
MedCode (Vals AI)41.0%39.3%GPT-5.4 Nano
SimpleQA Verified11.7%34.3%Kimi K2.5
LMArena Text: science13741459Kimi K2.5
LMArena Text: medicine and healthcare13691448Kimi K2.5
LMArena Text: legal and government13681441Kimi K2.5
LMArena Text: business and finance13661427Kimi K2.5
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for GPT-5.4 Nano and Kimi K2.5
BenchmarkGPT-5.4 NanoKimi K2.5Leader
Design Arena: websitesNot measured1248Only Kimi K2.5 measured
Design Arena: UI componentsNot measured1234Only Kimi K2.5 measured
Design Arena: game devNot measured1206Only Kimi K2.5 measured
Design Arena: data vizNot measured1219Only Kimi K2.5 measured
Design Arena: 3DNot measured1204Only Kimi K2.5 measured
Design Arena: all code categoriesNot measured1236Only Kimi K2.5 measured
Design Arena: SVGNot measured1149Only Kimi K2.5 measured
Design Arena: ASCII artNot measured1166Only Kimi K2.5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index226
General benchmarks for GPT-5.4 Nano and Kimi K2.5
BenchmarkGPT-5.4 NanoKimi K2.5Leader
SAGE (Vals AI)38.1%49.9%Kimi K2.5
MedScribe (Vals AI)77.1%76.4%GPT-5.4 Nano
Vals Multimodal Index47.6%Not measuredOnly GPT-5.4 Nano measured
IFBench75.9%70.2%GPT-5.4 Nano
Long context reasoning (AA-LCR)76.7%78.0%Kimi K2.5
DTBench80.3%Not measuredOnly GPT-5.4 Nano measured
LMCA36.9%Not measuredOnly GPT-5.4 Nano measured
Fiction.LiveBenchNot measured86.1%Only Kimi K2.5 measured
CL-benchNot measured19.3%Only Kimi K2.5 measured
CL-bench LifeNot measured13.2%Only Kimi K2.5 measured
LMArena Text13721445Kimi K2.5
LMArena Text: instruction following13621431Kimi K2.5
LMArena Text: creative writing13151422Kimi K2.5
LMArena Vision11961269Kimi K2.5
LMArena Text: English13811453Kimi K2.5
LMArena Text: non-English13591433Kimi K2.5
LMArena Text: Chinese13911494Kimi K2.5
LMArena Text: German13681441Kimi K2.5
LMArena Text: Japanese13431423Kimi K2.5
LMArena Text: Korean13211412Kimi K2.5
LMArena Text: French13951454Kimi K2.5
LMArena Text: Spanish13711450Kimi K2.5
LMArena Text: Russian13631435Kimi K2.5
LMArena Text: Polish13661445Kimi K2.5
LMArena Text: multi-turn13821444Kimi K2.5
LMArena Text: longer queries13651445Kimi K2.5
LMArena Text: writing and language13381425Kimi K2.5
LMArena Text: entertainment and media13251417Kimi K2.5
LMArena Vision: English12021274Kimi K2.5
LMArena Vision: Chinese12321328Kimi K2.5
LMArena Vision: reading text12041276Kimi K2.5
LMArena Vision: humor11611284Kimi K2.5
LMArena Vision: captioningNot measured1257Only Kimi K2.5 measured
LMArena Vision: recognizing things11411285Kimi K2.5
LMArena Vision: creative writing11591269Kimi K2.5
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.4 Nano and Kimi K2.5
BenchmarkGPT-5.4 NanoKimi K2.5Leader
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-5.4 Nano$0.0008Fits in one request
Kimi K2.5$0.0020Fits in one request

GPT-5.4 Nano costs less

Repository review

50K input + 3K output tokens

GPT-5.4 Nano$0.014Fits in one request
Kimi K2.5$0.035Fits in one request

GPT-5.4 Nano costs less

Agent loop

200K input + 10K output tokens

GPT-5.4 Nano$0.052Fits in one request
Kimi K2.5$0.135Fits in one request

GPT-5.4 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-5.4 Nano and Kimi K2.5
SpecificationOpenAI GPT-5.4 NanoMoonshotAI Kimi K2.5
MakerOpenAIMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedMarch 17, 2026January 27, 2026
Context window400K262K
Input $/Mtok$0.20$0.532
Output $/Mtok$1.25$2.85
Coding index44.838.6
Independent measurements behind it23
Cost per solved task$0.14$0.24
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.4 Nano better than Kimi K2.5 for coding?

Pick GPT-5.4 Nano for coding: it scores 44.8 on the Vibe Coding Index against 38.6 for Kimi K2.5, though on 2 benchmarks against 3. Pick Kimi K2.5 for work measured by SWE-bench Verified (Vals AI) or Terminal-Bench 2.1 (Vals AI), where it leads.

Which is cheaper, GPT-5.4 Nano or Kimi K2.5?

GPT-5.4 Nano costs $0.20 per million input tokens and $1.25 per million output tokens; Kimi K2.5 costs $0.532 and $2.85. Per solved SWE-bench Verified task, GPT-5.4 Nano costs $0.14 and Kimi K2.5 $0.24.

Which has the bigger context window, GPT-5.4 Nano or Kimi K2.5?

GPT-5.4 Nano, with 400K tokens against 262K.

How many benchmarks is the GPT-5.4 Nano vs Kimi K2.5 comparison based on?

71 benchmarks have a result for both models as of October 22, 2026. GPT-5.4 Nano's coding index rests on 2 independent benchmarks and Kimi K2.5's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/gpt-5-4-nano-vs-kimi-k2-5" title="GPT-5.4 Nano vs Kimi K2.5, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/gpt-5-4-nano-vs-kimi-k2-5">LLMBenchmark.ai, GPT-5.4 Nano vs Kimi K2.5</a></p>