Enter opens the highlighted result. Esc closes.

GPT-5.4 Mini vs Kimi K3

Kimi K3 leads GPT-5.4 Mini on coding, 62.3 to 35.8 on the Vibe Coding Index, and GPT-5.4 Mini costs 3.3x less per output token ($4.50 vs $15.00 per million). Updated October 22, 2026; 73 benchmarks have a result for both.

Replace GPT-5.4 Mini Replace Kimi K3
GPT-5.4 MiniOpenAI
Coding
35.8
Overall
44.0
Output $/M
$4.50
0
Kimi K3Moonshot AI
Coding
62.3
Overall
66.5
Output $/M
$15.00
73
vs boards won of 73 shared

GPT-5.4 Mini or Kimi K3: which to pick

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 35.8 for GPT-5.4 Mini.

Pick GPT-5.4 Mini for output tokens 3.3x cheaper ($4.50 vs $15.00 per million) and a lower cost per solved task ($0.70 against $0.81).

Model AGPT-5.4 MiniOpenAI35.8/1005 independent benchmarks$0.70 per solved taskModel BKimi K3Moonshot AI62.3/1006 independent benchmarks$0.81 per solved task
Shared results
73
GPT-5.4 Mini only
16
Kimi K3 only
44
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 Mini 35.8 from 5 benchmarks, Kimi K3 62.3 from 6 benchmarks.
Widest category
Math, 25.0 points apart on average over 6 shared benchmarks.
Widest single gap
ProofBench: GPT-5.4 Mini 21.0% against Kimi K3 87.0%, 66.0 points apart on a 0 to 100 scale.
Output price
GPT-5.4 Mini $4.50 against Kimi K3 $15.00 per million output tokens, 3.3x apart.
Context window
GPT-5.4 Mini takes 400K 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-5.4 MiniBarsKimi K3Ties
Coding017
Intelligence02
Agentic work05
Reasoning012
Math06
Knowledge09
General022
All shared boards073
CodingLike-for-likeSix of these boards feed the Vibe Coding Index017
Coding benchmarks for GPT-5.4 Mini and Kimi K3
BenchmarkGPT-5.4 MiniKimi K3Leader
LiveBench codingNot measured59.3%Only Kimi K3 measured
LMArena WebDev13971655Kimi K3
AA Coding Index56.176.2Kimi K3
LiveCodeBench (Vals AI)81.5%87.2%Kimi K3
SWE-bench Verified (Vals AI)73.0%93.4%Kimi K3
Terminal-Bench 4 (Vals AI)2.5%17.2%Kimi K3
Vibe Code Bench (Vals AI)48.0%85.0%Kimi K3
Code migration (Vals AI)12.9%16.1%Kimi K3
ProgramBench (Vals AI)0.0%2.0%Kimi K3
IOI (Vals AI)Not measured48.9%Only Kimi K3 measured
Terminal-Bench 2.1 (Vals AI)54.7%80.9%Kimi K3
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
CyberBench (Vals AI)Not measured75.2%Only Kimi K3 measured
SciCode52.1%59.5%Kimi K3
Terminal-Bench Hard (Artificial Analysis run)52.3%Not measuredOnly GPT-5.4 Mini measured
FrontierCode27.0%44.2%Kimi K3
FrontierSWENot measured25.9%Only Kimi K3 measured
WeirdML60.3%82.6%Kimi K3
ALE-Bench1188.61524.5Kimi K3
LMArena Text: coding14381508Kimi K3
LMArena Text: software and IT14361499Kimi K3
LMArena WebDev: React13861670Kimi K3
LMArena WebDev: HTML14191644Kimi K3
LMArena WebDev: from an imageNot measured1579Only Kimi K3 measured
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-5.4 Mini and Kimi K3
BenchmarkGPT-5.4 MiniKimi K3Leader
AA Intelligence Index24.143.6Kimi K3
Epoch Capabilities Index148.7157.9Kimi K3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index05
Agentic work benchmarks for GPT-5.4 Mini and Kimi K3
BenchmarkGPT-5.4 MiniKimi K3Leader
AA Agentic Index17.950.0Kimi K3
Design Arena: agents building web appsNot measured1295Only Kimi K3 measured
Design Arena: agents building full-stack appsNot measured1315Only Kimi K3 measured
Design Arena: agents building mobile appsNot measured1269Only Kimi K3 measured
Design Arena: agents building Android appsNot measured1253Only Kimi K3 measured
Design Arena: agents building Godot gamesNot measured1223Only Kimi K3 measured
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)45.4%53.1%Kimi K3
Tax Agent Bench (Vals AI)8.8%33.4%Kimi K3
Legal Research Bench (Vals AI)12.5%46.1%Kimi K3
Harvey's Legal Agent Benchmark (Vals AI)Not measured12.9%Only Kimi K3 measured
Excel Modeling Benchmark (Vals AI)45.4%66.7%Kimi K3
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 Telecom83.3%Not measuredOnly GPT-5.4 Mini measured
APEX-AgentsNot measured47.8%Only Kimi K3 measured
DeepResearch Bench36.3%Not measuredOnly GPT-5.4 Mini measured
PostTrainBenchNot measured32.0%Only Kimi K3 measured
Vending-Bench 2Not measured$5,165Only Kimi K3 measured
Neither model has a result on the other 15 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index012
Reasoning benchmarks for GPT-5.4 Mini and Kimi K3
BenchmarkGPT-5.4 MiniKimi K3Leader
GPQA Diamond83.1%92.9%Kimi K3
LiveBench reasoningNot measured90.7%Only Kimi K3 measured
MMMU Pro (Vals AI)79.3%88.2%Kimi K3
GPQA Diamond (Artificial Analysis run)87.5%93.5%Kimi K3
Humanity's Last Exam (Artificial Analysis run)28.1%46.9%Kimi K3
GPQA Diamond (Epoch AI run)86.9%93.1%Kimi K3
ARC-AGI63.7%94.5%Kimi K3
ARC-AGI-218.9%60.4%Kimi K3
SimpleBenchNot measured60.7%Only Kimi K3 measured
Chess puzzles23.0%37.0%Kimi K3
Mystery game puzzles11.0%26.0%Kimi K3
LMArena Text: hard prompts14241495Kimi K3
LMArena Text: expert14351520Kimi K3
LMArena Text: hard prompts in English14201496Kimi K3
LMArena Vision: diagrams1266Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: homework1285Not measuredOnly GPT-5.4 Mini measured
Kagi LLM Benchmark37.9%Not measuredOnly GPT-5.4 Mini measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index06
Math benchmarks for GPT-5.4 Mini and Kimi K3
BenchmarkGPT-5.4 MiniKimi K3Leader
AIME95.6%Not measuredOnly GPT-5.4 Mini measured
OTIS Mock AIME88.9%97.2%Kimi K3
FrontierMath, tiers 1 to 351.2%72.2%Kimi K3
FrontierMath, tier 49.8%39.0%Kimi K3
ProofBench21.0%87.0%Kimi K3
LMArena Text: math14181494Kimi K3
LMArena Text: mathematical work14291505Kimi K3
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index09
Knowledge benchmarks for GPT-5.4 Mini and Kimi K3
BenchmarkGPT-5.4 MiniKimi K3Leader
MMLU Pro84.5%88.0%Kimi K3
LegalBench (Vals AI)Not measured86.2%Only Kimi K3 measured
CaseLaw (Vals AI)51.7%Not measuredOnly GPT-5.4 Mini measured
CorpFin (Vals AI)60.9%71.6%Kimi K3
TaxEval (Vals AI)71.2%75.7%Kimi K3
MortgageTax (Vals AI)63.5%66.3%Kimi K3
MedCode (Vals AI)Not measured49.4%Only Kimi K3 measured
SimpleQA Verified29.4%50.6%Kimi K3
LMArena Text: science14171508Kimi K3
LMArena Text: medicine and healthcare13951489Kimi K3
LMArena Text: legal and government14141503Kimi K3
LMArena Text: business and finance14181470Kimi K3
Neither model has a result on the other 6 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for GPT-5.4 Mini and Kimi K3
BenchmarkGPT-5.4 MiniKimi K3Leader
Design Arena: websitesNot measured1334Only Kimi K3 measured
Design Arena: UI componentsNot measured1341Only Kimi K3 measured
Design Arena: game devNot measured1358Only Kimi K3 measured
Design Arena: data vizNot measured1351Only Kimi K3 measured
Design Arena: 3DNot measured1387Only Kimi K3 measured
Design Arena: all code categoriesNot measured1360Only Kimi K3 measured
Design Arena: SVGNot measured1302Only Kimi K3 measured
LiveBench designNot measured77.2%Only Kimi K3 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index022
General benchmarks for GPT-5.4 Mini and Kimi K3
BenchmarkGPT-5.4 MiniKimi 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)50.8%52.8%Kimi K3
MedScribe (Vals AI)Not measured88.0%Only Kimi K3 measured
Vals Multimodal Index54.2%73.4%Kimi K3
IFBench73.3%Not measuredOnly GPT-5.4 Mini measured
Long context reasoning (AA-LCR)77.0%88.7%Kimi K3
DTBench80.0%91.2%Kimi K3
LMCA40.8%52.7%Kimi K3
Surface Evolver BenchNot measured95.0%Only Kimi K3 measured
Furniture assemblyNot measured34.2%Only Kimi K3 measured
LMArena Text14121476Kimi K3
LMArena Text: instruction following14051485Kimi K3
LMArena Text: creative writing13701457Kimi K3
LMArena Vision1245Not measuredOnly GPT-5.4 Mini measured
LMArena Text: English14121481Kimi K3
LMArena Text: non-English14051466Kimi K3
LMArena Text: Chinese14461529Kimi K3
LMArena Text: German14081490Kimi K3
LMArena Text: Japanese13751494Kimi K3
LMArena Text: Korean13701460Kimi K3
LMArena Text: French14411492Kimi K3
LMArena Text: Spanish14051472Kimi K3
LMArena Text: Russian14171485Kimi K3
LMArena Text: Polish14151458Kimi K3
LMArena Text: multi-turn14291489Kimi K3
LMArena Text: longer queries14081494Kimi K3
LMArena Text: writing and language13931471Kimi K3
LMArena Text: entertainment and media13731453Kimi K3
LMArena Vision: English1244Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: Chinese1286Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: reading text1253Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: humor1235Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: recognizing things1218Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: creative writing1222Not measuredOnly GPT-5.4 Mini measured
Neither model has a result on the other 10 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.4 Mini and Kimi K3
BenchmarkGPT-5.4 MiniKimi 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 Mini$0.0030Fits in one request
Kimi K3$0.011Fits in one request

GPT-5.4 Mini costs less

Repository review

50K input + 3K output tokens

GPT-5.4 Mini$0.051Fits in one request
Kimi K3$0.195Fits in one request

GPT-5.4 Mini costs less

Agent loop

200K input + 10K output tokens

GPT-5.4 Mini$0.195Fits in one request
Kimi K3$0.750Fits in one request

GPT-5.4 Mini 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 Mini and Kimi K3
SpecificationOpenAI GPT-5.4 MiniMoonshotAI Kimi K3
MakerOpenAIMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedMarch 17, 2026July 16, 2026
Context window400K1.05M
Input $/Mtok$0.75$3.00
Output $/Mtok$4.50$15.00
Coding index35.862.3
Independent measurements behind it56
Cost per solved task$0.70$0.81
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.4 Mini better than Kimi K3 for coding?

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 35.8 for GPT-5.4 Mini. Pick GPT-5.4 Mini for output tokens 3.3x cheaper ($4.50 vs $15.00 per million) and a lower cost per solved task ($0.70 against $0.81).

Which is cheaper, GPT-5.4 Mini or Kimi K3?

GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens; Kimi K3 costs $3.00 and $15.00. Per solved SWE-bench Verified task, GPT-5.4 Mini costs $0.70 and Kimi K3 $0.81.

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

Kimi K3, with 1.05M tokens against 400K.

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

73 benchmarks have a result for both models as of October 22, 2026. GPT-5.4 Mini's coding index rests on 5 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-mini-vs-kimi-k3" title="GPT-5.4 Mini 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-mini-vs-kimi-k3">LLMBenchmark.ai, GPT-5.4 Mini vs Kimi K3</a></p>