Enter opens the highlighted result. Esc closes.

GPT-4o (2024-05-13) vs Kimi K2 Thinking

Kimi K2 Thinking leads GPT-4o (2024-05-13) on the Artificial Analysis Intelligence Index, 22.0 to 7.3, and Kimi K2 Thinking costs 6.0x less per output token ($2.50 vs $15.00 per million). Updated October 22, 2026; 7 benchmarks have a result for both.

Replace GPT-4o (2024-05-13) Replace Kimi K2 Thinking
GPT-4o (2024-05-13)OpenAI
Coding
No data
Overall
27.1
Output $/M
$15.00
0
Kimi K2 ThinkingMoonshot AI
Coding
No data
Overall
No data
Output $/M
$2.50
7
vs boards won of 7 shared

GPT-4o (2024-05-13) or Kimi K2 Thinking: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick GPT-4o (2024-05-13) for work measured by LiveCodeBench (Artificial Analysis run) or AA Intelligence Index, where it leads.

Model AGPT-4o (2024-05-13)OpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BKimi K2 ThinkingMoonshot AINot benchmarked1 independent benchmark$0.61 per solved task
Shared results
7
GPT-4o (2024-05-13) only
37
Kimi K2 Thinking only
23
Like-for-like categories
5 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-4o (2024-05-13) not benchmarked, Kimi K2 Thinking not benchmarked.
Widest category
Coding, 51.9 points apart on average over 1 shared benchmark.
Widest single gap
LiveCodeBench (Artificial Analysis run): GPT-4o (2024-05-13) 33.4% against Kimi K2 Thinking 85.3%, 51.9 points apart on a 0 to 100 scale.
Output price
GPT-4o (2024-05-13) $15.00 against Kimi K2 Thinking $2.50 per million output tokens, 6.0x apart.
Context window
GPT-4o (2024-05-13) takes 128K 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-4o (2024-05-13)BarsKimi K2 ThinkingTies
Coding01
Intelligence01
Agentic work01
Reasoning03
Knowledge01
All shared boards07
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
Coding benchmarks for GPT-4o (2024-05-13) and Kimi K2 Thinking
BenchmarkGPT-4o (2024-05-13)Kimi K2 ThinkingLeader
SWE-bench VerifiedNot measured63.4%Only Kimi K2 Thinking measured
AA Coding Index24.2Not measuredOnly GPT-4o (2024-05-13) measured
LiveCodeBench (Vals AI)Not measured63.1%Only Kimi K2 Thinking measured
SWE-bench Verified (Vals AI)Not measured60.2%Only Kimi K2 Thinking measured
LiveCodeBench (Artificial Analysis run)33.4%85.3%Kimi K2 Thinking
Terminal-Bench Hard (Artificial Analysis run)Not measured31.1%Only Kimi K2 Thinking measured
Terminal-BenchNot measured35.7%Only Kimi K2 Thinking measured
WeirdMLNot measured42.8%Only Kimi K2 Thinking measured
ALE-BenchNot measured597.5Only Kimi K2 Thinking measured
LMArena Text: coding1297Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: software and IT1297Not measuredOnly GPT-4o (2024-05-13) measured
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for GPT-4o (2024-05-13) and Kimi K2 Thinking
BenchmarkGPT-4o (2024-05-13)Kimi K2 ThinkingLeader
AA Intelligence Index7.322.0Kimi K2 Thinking
Epoch Capabilities IndexNot measured145.8Only Kimi K2 Thinking measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GPT-4o (2024-05-13) and Kimi K2 Thinking
BenchmarkGPT-4o (2024-05-13)Kimi K2 ThinkingLeader
τ²-Bench TelecomNot measured93.0%Only Kimi K2 Thinking measured
METR time horizons40.8%59.2%Kimi K2 Thinking
BALROG32.3%Not measuredOnly GPT-4o (2024-05-13) 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-4o (2024-05-13) and Kimi K2 Thinking
BenchmarkGPT-4o (2024-05-13)Kimi K2 ThinkingLeader
GPQA Diamond50.2%78.5%Kimi K2 Thinking
GPQA Diamond (Artificial Analysis run)52.6%83.8%Kimi K2 Thinking
Humanity's Last Exam (Artificial Analysis run)1.8%23.8%Kimi K2 Thinking
GPQA Diamond (Epoch AI run)48.9%Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: hard prompts1281Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: expert1250Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: hard prompts in English1293Not measuredOnly GPT-4o (2024-05-13) measured
Neither model has a result on the other 15 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Math benchmarks for GPT-4o (2024-05-13) and Kimi K2 Thinking
BenchmarkGPT-4o (2024-05-13)Kimi K2 ThinkingLeader
AIMENot measured85.4%Only Kimi K2 Thinking measured
MGSM (Vals AI)Not measured90.2%Only Kimi K2 Thinking measured
AA Math IndexNot measured94.7Only Kimi K2 Thinking measured
AIME 2025 (Artificial Analysis run)Not measured94.7%Only Kimi K2 Thinking measured
OTIS Mock AIME6.3%Not measuredOnly GPT-4o (2024-05-13) measured
MATH level 551.0%Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: math1284Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: mathematical work1284Not measuredOnly GPT-4o (2024-05-13) measured
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
Knowledge benchmarks for GPT-4o (2024-05-13) and Kimi K2 Thinking
BenchmarkGPT-4o (2024-05-13)Kimi K2 ThinkingLeader
MMLU ProNot measured81.1%Only Kimi K2 Thinking measured
LegalBench (Vals AI)Not measured80.2%Only Kimi K2 Thinking measured
CaseLaw (Vals AI)Not measured65.7%Only Kimi K2 Thinking measured
CorpFin (Vals AI)Not measured60.6%Only Kimi K2 Thinking measured
TaxEval (Vals AI)Not measured71.7%Only Kimi K2 Thinking measured
MedQA (Vals AI)Not measured92.6%Only Kimi K2 Thinking measured
MMLU Pro (Artificial Analysis run)74.0%84.8%Kimi K2 Thinking
MMLU84.2%Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: science1295Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: medicine and healthcare1278Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: legal and government1314Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: business and finance1262Not measuredOnly GPT-4o (2024-05-13) measured
Neither model has a result on the other 6 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Web design benchmarks for GPT-4o (2024-05-13) and Kimi K2 Thinking
BenchmarkGPT-4o (2024-05-13)Kimi K2 ThinkingLeader
Design Arena: websitesNot measured1113Only Kimi K2 Thinking measured
Neither model has a result on the other 8 boards here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index23 boards, none shared
General benchmarks for GPT-4o (2024-05-13) and Kimi K2 Thinking
BenchmarkGPT-4o (2024-05-13)Kimi K2 ThinkingLeader
IFBenchNot measured68.1%Only Kimi K2 Thinking measured
Long context reasoning (AA-LCR)Not measured72.0%Only Kimi K2 Thinking measured
CL-benchNot measured17.6%Only Kimi K2 Thinking measured
LMArena Text1300Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: instruction following1278Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: creative writing1291Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Vision1137Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: English1312Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: non-English1283Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: Chinese1277Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: German1283Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: Japanese1257Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: Korean1234Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: French1304Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: Spanish1292Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: Russian1285Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: Polish1365Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: multi-turn1302Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: longer queries1288Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: writing and language1298Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: entertainment and media1289Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Vision: English1147Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Vision: Chinese1132Not measuredOnly GPT-4o (2024-05-13) measured
Neither model has a result on the other 23 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4o (2024-05-13) and Kimi K2 Thinking
BenchmarkGPT-4o (2024-05-13)Kimi 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-4o (2024-05-13)$0.013Fits in one request
Kimi K2 Thinking$0.0019Fits in one request

Kimi K2 Thinking costs less

Repository review

50K input + 3K output tokens

GPT-4o (2024-05-13)$0.295Fits in one request
Kimi K2 Thinking$0.037Fits in one request

Kimi K2 Thinking costs less

Agent loop

200K input + 10K output tokens

GPT-4o (2024-05-13)$1.15Exceeds the context window
Kimi K2 Thinking$0.145Fits in one request

Kimi K2 Thinking 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-4o (2024-05-13) and Kimi K2 Thinking
SpecificationOpenAI GPT-4o (2024-05-13)MoonshotAI Kimi K2 Thinking
MakerOpenAIMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedMay 13, 2024November 6, 2025
Context window128K262K
Input $/Mtok$5.00$0.60
Output $/Mtok$15.00$2.50
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computable$0.61
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4o (2024-05-13) better than Kimi K2 Thinking for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4o (2024-05-13) for work measured by LiveCodeBench (Artificial Analysis run) or AA Intelligence Index, where it leads.

Which is cheaper, GPT-4o (2024-05-13) or Kimi K2 Thinking?

GPT-4o (2024-05-13) costs $5.00 per million input tokens and $15.00 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-4o (2024-05-13) or Kimi K2 Thinking?

Kimi K2 Thinking, with 262K tokens against 128K.

How many benchmarks is the GPT-4o (2024-05-13) vs Kimi K2 Thinking comparison based on?

7 benchmarks have a result for both models as of October 22, 2026. GPT-4o (2024-05-13)'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