Enter opens the highlighted result. Esc closes.

GPT-5.4 Mini vs Kimi K2.5

Kimi K2.5 leads GPT-5.4 Mini on coding, 38.6 to 35.8 on the Vibe Coding Index, and Kimi K2.5 costs 1.6x less per output token ($2.85 vs $4.50 per million). Updated October 22, 2026; 72 benchmarks have a result for both.

Replace GPT-5.4 Mini Replace Kimi K2.5
GPT-5.4 MiniOpenAI
Coding
35.8
Overall
44.0
Output $/M
$4.50
15
Kimi K2.5Moonshot AI
Coding
38.6
Overall
44.8
Output $/M
$2.85
56
vs boards won of 72 shared, 1 tied

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

Pick Kimi K2.5 for coding: it scores 38.6 on the Vibe Coding Index against 35.8 for GPT-5.4 Mini, though on 3 benchmarks against 5.

Pick GPT-5.4 Mini for a larger context window (400K against 262K tokens) and work measured by AA Coding Index or SWE-bench Verified (Vals AI), where it leads.

Model AGPT-5.4 MiniOpenAI35.8/1005 independent benchmarks$0.70 per solved taskModel BKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved task
Shared results
72
GPT-5.4 Mini only
17
Kimi K2.5 only
27
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 K2.5 38.6 from 3 benchmarks.
Widest category
Agentic work, 10.6 points apart on average over 4 shared benchmarks.
Widest single gap
Kagi LLM Benchmark: GPT-5.4 Mini 37.9% against Kimi K2.5 78.5%, 40.6 points apart on a 0 to 100 scale.
Output price
GPT-5.4 Mini $4.50 against Kimi K2.5 $2.85 per million output tokens, 1.6x apart.
Context window
GPT-5.4 Mini 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 MiniBarsKimi K2.5Ties
Coding86
Intelligence20
Agentic work22
Reasoning111
Math021 tie
Knowledge010
General225
All shared boards15561 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index86
Coding benchmarks for GPT-5.4 Mini and Kimi K2.5
BenchmarkGPT-5.4 MiniKimi K2.5Leader
SWE-bench VerifiedNot measured70.8%Only Kimi K2.5 measured
SWE-bench MultilingualNot measured67.3%Only Kimi K2.5 measured
LMArena WebDev13971437Kimi K2.5
AA Coding Index56.146.8GPT-5.4 Mini
LiveCodeBench (Vals AI)81.5%83.9%Kimi K2.5
SWE-bench Verified (Vals AI)73.0%70.0%GPT-5.4 Mini
Terminal-Bench 4 (Vals AI)2.5%Not measuredOnly GPT-5.4 Mini measured
Vibe Code Bench (Vals AI)48.0%17.5%GPT-5.4 Mini
Code migration (Vals AI)12.9%7.0%GPT-5.4 Mini
ProgramBench (Vals AI)0.0%Not measuredOnly GPT-5.4 Mini measured
Terminal-Bench 2.1 (Vals AI)54.7%42.0%GPT-5.4 Mini
SciCode52.1%Not measuredOnly GPT-5.4 Mini measured
Terminal-Bench Hard (Artificial Analysis run)52.3%34.8%GPT-5.4 Mini
Terminal-BenchNot measured43.2%Only Kimi K2.5 measured
FrontierCode27.0%Not measuredOnly GPT-5.4 Mini measured
WeirdML60.3%45.6%GPT-5.4 Mini
ALE-Bench1188.6821.6GPT-5.4 Mini
LMArena Text: coding14381483Kimi K2.5
LMArena Text: software and IT14361471Kimi K2.5
LMArena WebDev: React13861429Kimi K2.5
LMArena WebDev: HTML14191426Kimi K2.5
LMArena WebDev: from an imageNot measured1439Only Kimi K2.5 measured
Neither model has a result on the other 17 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5.4 Mini and Kimi K2.5
BenchmarkGPT-5.4 MiniKimi K2.5Leader
AA Intelligence Index24.123.5GPT-5.4 Mini
Epoch Capabilities Index148.7148.1GPT-5.4 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index22
Agentic work benchmarks for GPT-5.4 Mini and Kimi K2.5
BenchmarkGPT-5.4 MiniKimi K2.5Leader
AA Agentic Index17.9Not measuredOnly GPT-5.4 Mini 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)45.4%35.8%GPT-5.4 Mini
Tax Agent Bench (Vals AI)8.8%Not measuredOnly GPT-5.4 Mini measured
Legal Research Bench (Vals AI)12.5%15.9%Kimi K2.5
Excel Modeling Benchmark (Vals AI)45.4%28.5%GPT-5.4 Mini
τ²-Bench Telecom83.3%95.9%Kimi K2.5
DeepResearch Bench36.3%Not measuredOnly GPT-5.4 Mini measured
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 27 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index111
Reasoning benchmarks for GPT-5.4 Mini and Kimi K2.5
BenchmarkGPT-5.4 MiniKimi K2.5Leader
GPQA Diamond83.1%84.1%Kimi K2.5
MMMU Pro (Vals AI)79.3%84.3%Kimi K2.5
GPQA Diamond (Artificial Analysis run)87.5%87.9%Kimi K2.5
Humanity's Last Exam (Artificial Analysis run)28.1%30.7%Kimi K2.5
GPQA Diamond (Epoch AI run)86.9%Not measuredOnly GPT-5.4 Mini measured
ARC-AGI63.7%65.3%Kimi K2.5
ARC-AGI-218.9%11.8%GPT-5.4 Mini
SimpleBenchNot measured46.8%Only Kimi K2.5 measured
Chess puzzles23.0%Not measuredOnly GPT-5.4 Mini measured
Mystery game puzzles11.0%Not measuredOnly GPT-5.4 Mini measured
LMArena Text: hard prompts14241453Kimi K2.5
LMArena Text: expert14351466Kimi K2.5
LMArena Text: hard prompts in English14201460Kimi K2.5
LMArena Vision: diagrams12661282Kimi K2.5
LMArena Vision: homework12851297Kimi K2.5
Kagi LLM Benchmark37.9%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 index02
Math benchmarks for GPT-5.4 Mini and Kimi K2.5
BenchmarkGPT-5.4 MiniKimi K2.5Leader
AIME95.6%95.6%Tie
OTIS Mock AIME88.9%Not measuredOnly GPT-5.4 Mini measured
FrontierMath, tiers 1 to 351.2%Not measuredOnly GPT-5.4 Mini measured
FrontierMath, tier 49.8%Not measuredOnly GPT-5.4 Mini measured
ProofBench21.0%Not measuredOnly GPT-5.4 Mini measured
LMArena Text: math14181470Kimi K2.5
LMArena Text: mathematical work14291473Kimi K2.5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index010
Knowledge benchmarks for GPT-5.4 Mini and Kimi K2.5
BenchmarkGPT-5.4 MiniKimi K2.5Leader
MMLU Pro84.5%85.9%Kimi K2.5
CaseLaw (Vals AI)51.7%58.7%Kimi K2.5
CorpFin (Vals AI)60.9%68.3%Kimi K2.5
TaxEval (Vals AI)71.2%74.2%Kimi K2.5
MortgageTax (Vals AI)63.5%66.5%Kimi K2.5
MedQA (Vals AI)Not measured94.4%Only Kimi K2.5 measured
MedCode (Vals AI)Not measured39.3%Only Kimi K2.5 measured
SimpleQA Verified29.4%34.3%Kimi K2.5
LMArena Text: science14171459Kimi K2.5
LMArena Text: medicine and healthcare13951448Kimi K2.5
LMArena Text: legal and government14141441Kimi K2.5
LMArena Text: business and finance14181427Kimi K2.5
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 K2.5
BenchmarkGPT-5.4 MiniKimi 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 index225
General benchmarks for GPT-5.4 Mini and Kimi K2.5
BenchmarkGPT-5.4 MiniKimi K2.5Leader
SAGE (Vals AI)50.8%49.9%GPT-5.4 Mini
MedScribe (Vals AI)Not measured76.4%Only Kimi K2.5 measured
Vals Multimodal Index54.2%Not measuredOnly GPT-5.4 Mini measured
IFBench73.3%70.2%GPT-5.4 Mini
Long context reasoning (AA-LCR)77.0%78.0%Kimi K2.5
DTBench80.0%Not measuredOnly GPT-5.4 Mini measured
LMCA40.8%Not measuredOnly GPT-5.4 Mini 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 Text14121445Kimi K2.5
LMArena Text: instruction following14051431Kimi K2.5
LMArena Text: creative writing13701422Kimi K2.5
LMArena Vision12451269Kimi K2.5
LMArena Text: English14121453Kimi K2.5
LMArena Text: non-English14051433Kimi K2.5
LMArena Text: Chinese14461494Kimi K2.5
LMArena Text: German14081441Kimi K2.5
LMArena Text: Japanese13751423Kimi K2.5
LMArena Text: Korean13701412Kimi K2.5
LMArena Text: French14411454Kimi K2.5
LMArena Text: Spanish14051450Kimi K2.5
LMArena Text: Russian14171435Kimi K2.5
LMArena Text: Polish14151445Kimi K2.5
LMArena Text: multi-turn14291444Kimi K2.5
LMArena Text: longer queries14081445Kimi K2.5
LMArena Text: writing and language13931425Kimi K2.5
LMArena Text: entertainment and media13731417Kimi K2.5
LMArena Vision: English12441274Kimi K2.5
LMArena Vision: Chinese12861328Kimi K2.5
LMArena Vision: reading text12531276Kimi K2.5
LMArena Vision: humor12351284Kimi K2.5
LMArena Vision: captioningNot measured1257Only Kimi K2.5 measured
LMArena Vision: recognizing things12181285Kimi K2.5
LMArena Vision: creative writing12221269Kimi 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 Mini and Kimi K2.5
BenchmarkGPT-5.4 MiniKimi 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 Mini$0.0030Fits in one request
Kimi K2.5$0.0020Fits in one request

Kimi K2.5 costs less

Repository review

50K input + 3K output tokens

GPT-5.4 Mini$0.051Fits in one request
Kimi K2.5$0.035Fits in one request

Kimi K2.5 costs less

Agent loop

200K input + 10K output tokens

GPT-5.4 Mini$0.195Fits in one request
Kimi K2.5$0.135Fits in one request

Kimi K2.5 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 K2.5
SpecificationOpenAI GPT-5.4 MiniMoonshotAI Kimi K2.5
MakerOpenAIMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedMarch 17, 2026January 27, 2026
Context window400K262K
Input $/Mtok$0.75$0.532
Output $/Mtok$4.50$2.85
Coding index35.838.6
Independent measurements behind it53
Cost per solved task$0.70$0.24
SourceOpenRouter listingOpenRouter listing

Questions

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

Pick Kimi K2.5 for coding: it scores 38.6 on the Vibe Coding Index against 35.8 for GPT-5.4 Mini, though on 3 benchmarks against 5. Pick GPT-5.4 Mini for a larger context window (400K against 262K tokens) and work measured by AA Coding Index or SWE-bench Verified (Vals AI), where it leads.

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

GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens; Kimi K2.5 costs $0.532 and $2.85. Per solved SWE-bench Verified task, GPT-5.4 Mini costs $0.70 and Kimi K2.5 $0.24.

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

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

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

72 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 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-mini-vs-kimi-k2-5" title="GPT-5.4 Mini 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-mini-vs-kimi-k2-5">LLMBenchmark.ai, GPT-5.4 Mini vs Kimi K2.5</a></p>