Enter opens the highlighted result. Esc closes.

GPT-5.4 vs Kimi K3

GPT-5.4 leads Kimi K3 on coding, 64.4 to 62.3 on the Vibe Coding Index, at about the same output price ($15.00 vs $15.00 per million). Updated October 22, 2026; 83 benchmarks have a result for both.

Replace GPT-5.4 Replace Kimi K3
GPT-5.4OpenAI
Coding
64.4
Overall
69.6
Output $/M
$15.00
17
Kimi K3Moonshot AI
Coding
62.3
Overall
66.5
Output $/M
$15.00
66
vs boards won of 83 shared

GPT-5.4 or Kimi K3: which to pick

Pick GPT-5.4 for coding: it scores 64.4 on the Vibe Coding Index against 62.3 for Kimi K3, though on 3 benchmarks against 6.

Pick Kimi K3 for a lower cost per solved task ($0.81 against $1.02) and work measured by LMArena WebDev or AA Coding Index, where it leads.

Model AGPT-5.4OpenAI64.4/1003 independent benchmarks$1.02 per solved taskModel BKimi K3Moonshot AI62.3/1006 independent benchmarks$0.81 per solved task
Shared results
83
GPT-5.4 only
27
Kimi K3 only
34
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-5.4 64.4 from 3 benchmarks, Kimi K3 62.3 from 6 benchmarks.
Widest category
Web design, 22.3 points apart on average over 7 shared benchmarks.
Widest single gap
Design Arena: 3D: GPT-5.4 1065 against Kimi K3 1387, 40.3 points apart on a 0 to 100 scale.
Output price
Both cost $15.00 per million output tokens.
Context window
GPT-5.4 takes 1.05M tokens, Kimi K3 1.05M.

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-5.4BarsKimi K3Ties
Coding212
Intelligence02
Agentic work26
Reasoning48
Math33
Knowledge29
Web design07
General419
All shared boards1766
CodingLike-for-likeSix of these boards feed the Vibe Coding Index212
Coding benchmarks for GPT-5.4 and Kimi K3
BenchmarkGPT-5.4Kimi K3Leader
LiveBench codingNot measured59.3%Only Kimi K3 measured
LMArena WebDev14641655Kimi K3
AA Coding Index71.176.2Kimi K3
LiveCodeBench (Vals AI)84.1%87.2%Kimi K3
SWE-bench Verified (Vals AI)78.2%93.4%Kimi K3
Terminal-Bench 4 (Vals AI)Not measured17.2%Only Kimi K3 measured
Vibe Code Bench (Vals AI)67.4%85.0%Kimi K3
Code migration (Vals AI)35.0%16.1%GPT-5.4
ProgramBench (Vals AI)0.5%2.0%Kimi K3
IOI (Vals AI)Not measured48.9%Only Kimi K3 measured
Terminal-Bench 2.1 (Vals AI)Not measured80.9%Only Kimi K3 measured
SWE-bench Multimodal (Vals AI)Not measured44.2%Only Kimi K3 measured
Vibe Code Bench 1-100 (Vals AI)Not measured18.2%Only Kimi K3 measured
SkillsBench (Vals AI)51.7%Not measuredOnly GPT-5.4 measured
CyberBench (Vals AI)Not measured75.2%Only Kimi K3 measured
SciCodeNot measured59.5%Only Kimi K3 measured
Terminal-Bench Hard (Artificial Analysis run)57.6%Not measuredOnly GPT-5.4 measured
Terminal-Bench81.8%Not measuredOnly GPT-5.4 measured
FrontierCodeNot measured44.2%Only Kimi K3 measured
FrontierSWENot measured25.9%Only Kimi K3 measured
GSO-Bench31.4%Not measuredOnly GPT-5.4 measured
WeirdML77.7%82.6%Kimi K3
MirrorCode15.6%Not measuredOnly GPT-5.4 measured
ALE-Bench1607.01524.5GPT-5.4
LMArena Text: coding14961508Kimi K3
LMArena Text: software and IT14911499Kimi K3
LMArena WebDev: React14541670Kimi K3
LMArena WebDev: HTML14781644Kimi K3
LMArena WebDev: from an image14361579Kimi K3
Neither model has a result on the other 10 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-5.4 and Kimi K3
BenchmarkGPT-5.4Kimi K3Leader
AA Intelligence Index39.043.6Kimi K3
Epoch Capabilities Index157.3157.9Kimi K3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index26
Agentic work benchmarks for GPT-5.4 and Kimi K3
BenchmarkGPT-5.4Kimi K3Leader
AA Agentic IndexNot measured50.0Only Kimi K3 measured
Design Arena: agents building web apps10591295Kimi K3
Design Arena: agents building full-stack apps10171315Kimi K3
Design Arena: agents building mobile apps10871269Kimi K3
Design Arena: agents building Android apps10311253Kimi K3
Design Arena: agents building Godot games11351223Kimi K3
Design Arena: agents building gamesNot measured1252Only Kimi K3 measured
Design Arena: HTML slidesNot measured1206Only Kimi K3 measured
Design Arena: PowerPoint slidesNot measured1247Only Kimi K3 measured
Design Arena: spreadsheetsNot measured1070Only Kimi K3 measured
LiveBench researchNot measured79.0%Only Kimi K3 measured
LiveBench browserNot measured16.0%Only Kimi K3 measured
LiveBench long agenticNot measured42.8%Only Kimi K3 measured
Finance Agent (Vals AI)Not measured53.1%Only Kimi K3 measured
Tax Agent Bench (Vals AI)Not measured33.4%Only Kimi K3 measured
Legal Research Bench (Vals AI)Not measured46.1%Only Kimi K3 measured
Harvey's Legal Agent Benchmark (Vals AI)Not measured12.9%Only Kimi K3 measured
Excel Modeling Benchmark (Vals AI)Not measured66.7%Only Kimi K3 measured
BioMysteryBench (Vals AI)Not measured72.6%Only Kimi K3 measured
Terminal-Bench-Science (Vals AI)Not measured1.4%Only Kimi K3 measured
Time Horizon Index (Vals AI)Not measured10.5%Only Kimi K3 measured
τ²-Bench Telecom87.1%Not measuredOnly GPT-5.4 measured
APEX-Agents52.4%47.8%GPT-5.4
METR time horizons74.3%Not measuredOnly GPT-5.4 measured
DeepResearch Bench35.1%Not measuredOnly GPT-5.4 measured
PostTrainBench19.0%32.0%Kimi K3
Vending-Bench 2$6,144$5,165GPT-5.4
Neither model has a result on the other 14 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index48
Reasoning benchmarks for GPT-5.4 and Kimi K3
BenchmarkGPT-5.4Kimi K3Leader
GPQA Diamond91.7%92.9%Kimi K3
LiveBench reasoningNot measured90.7%Only Kimi K3 measured
MMMU Pro (Vals AI)87.5%88.2%Kimi K3
GPQA Diamond (Artificial Analysis run)92.0%93.5%Kimi K3
Humanity's Last Exam (Artificial Analysis run)43.7%46.9%Kimi K3
GPQA Diamond (Epoch AI run)93.3%93.1%GPT-5.4
ARC-AGI93.7%94.5%Kimi K3
ARC-AGI-274.0%60.4%GPT-5.4
SimpleBenchNot measured60.7%Only Kimi K3 measured
Chess puzzles48.0%37.0%GPT-5.4
Mystery game puzzles37.0%26.0%GPT-5.4
EBR-bench25.4%Not measuredOnly GPT-5.4 measured
LMArena Text: hard prompts14851495Kimi K3
LMArena Text: expert15071520Kimi K3
LMArena Text: hard prompts in English14791496Kimi K3
LMArena Vision: diagrams1327Not measuredOnly GPT-5.4 measured
LMArena Vision: homework1336Not measuredOnly GPT-5.4 measured
Kagi LLM Benchmark63.8%Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index33
Math benchmarks for GPT-5.4 and Kimi K3
BenchmarkGPT-5.4Kimi K3Leader
AIME96.7%Not measuredOnly GPT-5.4 measured
OTIS Mock AIME97.8%97.2%GPT-5.4
FrontierMath, tiers 1 to 378.6%72.2%GPT-5.4
FrontierMath, tier 449.0%39.0%GPT-5.4
ProofBench56.0%87.0%Kimi K3
LMArena Text: math14881494Kimi K3
LMArena Text: mathematical work14971505Kimi K3
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index29
Knowledge benchmarks for GPT-5.4 and Kimi K3
BenchmarkGPT-5.4Kimi K3Leader
MMLU Pro87.5%88.0%Kimi K3
LegalBench (Vals AI)86.0%86.2%Kimi K3
CaseLaw (Vals AI)63.8%Not measuredOnly GPT-5.4 measured
CorpFin (Vals AI)65.3%71.6%Kimi K3
TaxEval (Vals AI)74.0%75.7%Kimi K3
MortgageTax (Vals AI)68.3%66.3%GPT-5.4
MedQA (Vals AI)96.1%Not measuredOnly GPT-5.4 measured
MedCode (Vals AI)41.3%49.4%Kimi K3
SimpleQA Verified45.1%50.6%Kimi K3
LMArena Text: science14791508Kimi K3
LMArena Text: medicine and healthcare14581489Kimi K3
LMArena Text: legal and government14861503Kimi K3
LMArena Text: business and finance14741470GPT-5.4
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for GPT-5.4 and Kimi K3
BenchmarkGPT-5.4Kimi K3Leader
Design Arena: websites11981334Kimi K3
Design Arena: UI components12121341Kimi K3
Design Arena: game dev11941358Kimi K3
Design Arena: data viz11961351Kimi K3
Design Arena: 3D10651387Kimi K3
Design Arena: all code categories11791360Kimi K3
Design Arena: SVG11411302Kimi K3
Design Arena: ASCII art1188Not measuredOnly GPT-5.4 measured
LiveBench designNot measured77.2%Only Kimi K3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index419
General benchmarks for GPT-5.4 and Kimi K3
BenchmarkGPT-5.4Kimi K3Leader
Vals IndexNot measured53.0%Only Kimi K3 measured
LiveBench data analysisNot measured78.7%Only Kimi K3 measured
Public Benefits Bench (Vals AI)Not measured68.2%Only Kimi K3 measured
SAGE (Vals AI)43.3%52.8%Kimi K3
MedScribe (Vals AI)77.5%88.0%Kimi K3
Vals Multimodal IndexNot measured73.4%Only Kimi K3 measured
IFBench73.9%Not measuredOnly GPT-5.4 measured
Long context reasoning (AA-LCR)82.0%88.7%Kimi K3
DTBench94.4%91.2%GPT-5.4
LMCA52.0%52.7%Kimi K3
CL-bench27.9%Not measuredOnly GPT-5.4 measured
Surface Evolver BenchNot measured95.0%Only Kimi K3 measured
Furniture assembly37.5%34.2%GPT-5.4
CL-bench Life21.7%Not measuredOnly GPT-5.4 measured
LMArena Text14691476Kimi K3
LMArena Text: instruction following14691485Kimi K3
LMArena Text: creative writing14391457Kimi K3
LMArena Vision1303Not measuredOnly GPT-5.4 measured
LMArena Text: English14671481Kimi K3
LMArena Text: non-English14651466Kimi K3
LMArena Text: Chinese15201529Kimi K3
LMArena Text: German14721490Kimi K3
LMArena Text: Japanese14851494Kimi K3
LMArena Text: Korean14491460Kimi K3
LMArena Text: French14931492GPT-5.4
LMArena Text: Spanish14521472Kimi K3
LMArena Text: Russian14801485Kimi K3
LMArena Text: Polish14721458GPT-5.4
LMArena Text: multi-turn14821489Kimi K3
LMArena Text: longer queries14731494Kimi K3
LMArena Text: writing and language14581471Kimi K3
LMArena Text: entertainment and media14381453Kimi K3
LMArena Vision: English1301Not measuredOnly GPT-5.4 measured
LMArena Vision: Chinese1354Not measuredOnly GPT-5.4 measured
LMArena Vision: reading text1312Not measuredOnly GPT-5.4 measured
LMArena Vision: humor1284Not measuredOnly GPT-5.4 measured
LMArena Vision: recognizing things1251Not measuredOnly GPT-5.4 measured
LMArena Vision: creative writing1283Not measuredOnly GPT-5.4 measured
LMArena Document1471Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 7 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.4 and Kimi K3
BenchmarkGPT-5.4Kimi K3Leader
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$0.010Fits in one request
Kimi K3$0.011Fits in one request

GPT-5.4 costs less

Repository review

50K input + 3K output tokens

GPT-5.4$0.170Fits in one request
Kimi K3$0.195Fits in one request

GPT-5.4 costs less

Agent loop

200K input + 10K output tokens

GPT-5.4$0.650Fits in one request
Kimi K3$0.750Fits in one request

GPT-5.4 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 and Kimi K3
SpecificationOpenAI GPT-5.4MoonshotAI Kimi K3
MakerOpenAIMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedMarch 5, 2026July 16, 2026
Context window1.05M1.05M
Input $/Mtok$2.50$3.00
Output $/Mtok$15.00$15.00
Coding index64.462.3
Independent measurements behind it36
Cost per solved task$1.02$0.81
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.4 better than Kimi K3 for coding?

Pick GPT-5.4 for coding: it scores 64.4 on the Vibe Coding Index against 62.3 for Kimi K3, though on 3 benchmarks against 6. Pick Kimi K3 for a lower cost per solved task ($0.81 against $1.02) and work measured by LMArena WebDev or AA Coding Index, where it leads.

Which is cheaper, GPT-5.4 or Kimi K3?

GPT-5.4 costs $2.50 per million input tokens and $15.00 per million output tokens; Kimi K3 costs $3.00 and $15.00. Per solved SWE-bench Verified task, GPT-5.4 costs $1.02 and Kimi K3 $0.81.

Which has the bigger context window, GPT-5.4 or Kimi K3?

GPT-5.4, with 1.05M tokens against 1.05M.

How many benchmarks is the GPT-5.4 vs Kimi K3 comparison based on?

83 benchmarks have a result for both models as of October 22, 2026. GPT-5.4's coding index rests on 3 independent benchmarks and Kimi K3's on 6. 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-vs-kimi-k3" title="GPT-5.4 vs Kimi K3, 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-vs-kimi-k3">LLMBenchmark.ai, GPT-5.4 vs Kimi K3</a></p>