Enter opens the highlighted result. Esc closes.

DeepSeek V3.1 vs Kimi K2.7 Code

Updated October 21, 2026. 8 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace DeepSeek V3.1 Replace Kimi K2.7 Code
DeepSeek V3.1DeepSeek
Coding
No data
Overall
13.7
Output $/M
$1.50
0
Kimi K2.7 CodeMoonshot AI
Coding
53.4
Overall
25.8
Output $/M
$4.00
8
vs boards won of 8 shared

Decision reading

Only Kimi K2.7 Code has a coding score, 53.4 on the Vibe Coding Index; DeepSeek V3.1 has none, so the two cannot be ranked on coding.

DeepSeek V3.1 has the edge where output tokens cost 2.7x less.

Model ADeepSeek V3.1DeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BKimi K2.7 CodeMoonshot AI53.4/1004 independent benchmarks$0.35 per solved task
Shared results
8
DeepSeek V3.1 only
2
Kimi K2.7 Code only
43
Like-for-like categories
2 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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
DeepSeek V3.1 not benchmarked, Kimi K2.7 Code 53.4 from 4 benchmarks.
Widest category
Web design, 19.6 points apart on average over 7 shared benchmarks.
Widest single gap
Design Arena: SVG: DeepSeek V3.1 967 against Kimi K2.7 Code 1176, 26.1 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.1 $1.50 against Kimi K2.7 Code $4.00 per million output tokens, 2.7x apart.
Context window
DeepSeek V3.1 takes 164K tokens, Kimi K2.7 Code 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
CategoryDeepSeek V3.1BarsKimi K2.7 CodeTies
Intelligence01
Web design07
All shared boards08
CodingDirectional onlySix of these boards feed the Vibe Coding Index17 boards, none shared
Coding benchmarks for DeepSeek V3.1 and Kimi K2.7 Code
BenchmarkDeepSeek V3.1Kimi K2.7 CodeLeader
LMArena WebDevNot measured1474Only Kimi K2.7 Code measured
AA Coding IndexNot measured60.8Only Kimi K2.7 Code measured
LiveCodeBench (Vals AI)Not measured82.0%Only Kimi K2.7 Code measured
SWE-bench Verified (Vals AI)Not measured78.2%Only Kimi K2.7 Code measured
Vibe Code Bench (Vals AI)Not measured47.2%Only Kimi K2.7 Code measured
Code migration (Vals AI)Not measured25.4%Only Kimi K2.7 Code measured
ProgramBench (Vals AI)Not measured0.0%Only Kimi K2.7 Code measured
Terminal-Bench 2.1 (Vals AI)Not measured67.0%Only Kimi K2.7 Code measured
SkillsBench (Vals AI)Not measured50.0%Only Kimi K2.7 Code measured
SciCodeNot measured47.8%Only Kimi K2.7 Code measured
Terminal-Bench Hard (Artificial Analysis run)Not measured44.7%Only Kimi K2.7 Code measured
FrontierCodeNot measured30.1%Only Kimi K2.7 Code measured
WeirdMLNot measured54.1%Only Kimi K2.7 Code measured
ALE-BenchNot measured886.2Only Kimi K2.7 Code measured
LMArena WebDev: ReactNot measured1475Only Kimi K2.7 Code measured
LMArena WebDev: HTMLNot measured1451Only Kimi K2.7 Code measured
LMArena WebDev: from an imageNot measured1513Only Kimi K2.7 Code measured
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for DeepSeek V3.1 and Kimi K2.7 Code
BenchmarkDeepSeek V3.1Kimi K2.7 CodeLeader
AA Intelligence Index13.725.8Kimi K2.7 Code
Epoch Capabilities IndexNot measured150.1Only Kimi K2.7 Code measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
Agentic work benchmarks for DeepSeek V3.1 and Kimi K2.7 Code
BenchmarkDeepSeek V3.1Kimi K2.7 CodeLeader
AA Agentic IndexNot measured21.0Only Kimi K2.7 Code measured
Design Arena: agents building web appsNot measured1176Only Kimi K2.7 Code measured
Design Arena: agents building full-stack appsNot measured1175Only Kimi K2.7 Code measured
Design Arena: agents building mobile appsNot measured1143Only Kimi K2.7 Code measured
Design Arena: agents building Android appsNot measured1143Only Kimi K2.7 Code measured
Design Arena: agents building Godot gamesNot measured1147Only Kimi K2.7 Code measured
Design Arena: agents building gamesNot measured1131Only Kimi K2.7 Code measured
Design Arena: HTML slidesNot measured1201Only Kimi K2.7 Code measured
Design Arena: PowerPoint slidesNot measured1154Only Kimi K2.7 Code measured
τ²-Bench TelecomNot measured90.1%Only Kimi K2.7 Code measured
APEX-AgentsNot measured37.6%Only Kimi K2.7 Code measured
Vending-Bench 2Not measured$5,083Only Kimi K2.7 Code measured
Neither model has a result on the other 27 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Reasoning benchmarks for DeepSeek V3.1 and Kimi K2.7 Code
BenchmarkDeepSeek V3.1Kimi K2.7 CodeLeader
GPQA Diamond (Artificial Analysis run)Not measured89.6%Only Kimi K2.7 Code measured
Humanity's Last Exam (Artificial Analysis run)Not measured35.0%Only Kimi K2.7 Code measured
GPQA Diamond (Epoch AI run)Not measured87.9%Only Kimi K2.7 Code measured
SimpleBenchNot measured57.9%Only Kimi K2.7 Code measured
Chess puzzlesNot measured14.0%Only Kimi K2.7 Code measured
Neither model has a result on the other 16 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Math benchmarks for DeepSeek V3.1 and Kimi K2.7 Code
BenchmarkDeepSeek V3.1Kimi K2.7 CodeLeader
OTIS Mock AIMENot measured95.6%Only Kimi K2.7 Code measured
FrontierMath, tiers 1 to 3Not measured54.0%Only Kimi K2.7 Code measured
FrontierMath, tier 4Not measured12.2%Only Kimi K2.7 Code measured
Neither model has a result on the other 10 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Knowledge benchmarks for DeepSeek V3.1 and Kimi K2.7 Code
BenchmarkDeepSeek V3.1Kimi K2.7 CodeLeader
SimpleQA VerifiedNot measured36.5%Only Kimi K2.7 Code measured
Neither model has a result on the other 16 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for DeepSeek V3.1 and Kimi K2.7 Code
BenchmarkDeepSeek V3.1Kimi K2.7 CodeLeader
Design Arena: websites11231264Kimi K2.7 Code
Design Arena: UI components10851259Kimi K2.7 Code
Design Arena: game dev10841220Kimi K2.7 Code
Design Arena: data viz10951227Kimi K2.7 Code
Design Arena: 3D10771241Kimi K2.7 Code
Design Arena: all code categories11121253Kimi K2.7 Code
Design Arena: SVG9671176Kimi K2.7 Code
Design Arena: ASCII artNot measured1196Only Kimi K2.7 Code measured
Neither model has a result on the other 1 board here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
General benchmarks for DeepSeek V3.1 and Kimi K2.7 Code
BenchmarkDeepSeek V3.1Kimi K2.7 CodeLeader
IFBenchNot measured63.1%Only Kimi K2.7 Code measured
Long context reasoning (AA-LCR)Not measured79.3%Only Kimi K2.7 Code measured
DTBench82.7%Not measuredOnly DeepSeek V3.1 measured
LMCA24.3%Not measuredOnly DeepSeek V3.1 measured
Surface Evolver BenchNot measured48.8%Only Kimi K2.7 Code measured
Neither model has a result on the other 41 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3.1 and Kimi K2.7 Code
BenchmarkDeepSeek V3.1Kimi K2.7 CodeLeader
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

DeepSeek V3.1$0.0013Fits in one request
Kimi K2.7 Code$0.0029Fits in one request

DeepSeek V3.1 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.1$0.032Fits in one request
Kimi K2.7 Code$0.059Fits in one request

DeepSeek V3.1 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.1$0.125Exceeds the context window
Kimi K2.7 Code$0.230Fits in one request

DeepSeek V3.1 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 DeepSeek V3.1 and Kimi K2.7 Code
SpecificationDeepSeek V3.1MoonshotAI Kimi K2.7 Code
MakerDeepSeekMoonshot AI
WeightsOpen weightsOpen weights
ReleasedAugust 21, 2025June 12, 2026
Context window164K262K
Input $/Mtok$0.55$0.95
Output $/Mtok$1.50$4.00
Coding indexNot benchmarked53.4
Independent measurements behind it04
Cost per solved taskNot computable$0.35
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.1 better than Kimi K2.7 Code for coding?

Only Kimi K2.7 Code has a coding score, 53.4 on the Vibe Coding Index; DeepSeek V3.1 has none, so the two cannot be ranked on coding. DeepSeek V3.1 has the edge where output tokens cost 2.7x less.

Which is cheaper, DeepSeek V3.1 or Kimi K2.7 Code?

DeepSeek V3.1 costs $0.55 per million input tokens and $1.50 per million output tokens; Kimi K2.7 Code costs $0.95 and $4.00. Cost per solved task is known for Kimi K2.7 Code only.

Which has the bigger context window, DeepSeek V3.1 or Kimi K2.7 Code?

Kimi K2.7 Code, with 262K tokens against 164K.

How many benchmarks is the DeepSeek V3.1 vs Kimi K2.7 Code comparison based on?

8 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.1's coding index rests on 0 independent benchmarks and Kimi K2.7 Code's on 4. Where only one model has a result, the page says so instead of naming a winner.

Compare next