Enter opens the highlighted result. Esc closes.

DeepSeek V4 Flash 0731 vs Kimi K2 0905

DeepSeek V4 Flash 0731 leads Kimi K2 0905 on the Artificial Analysis Intelligence Index, 34.3 to 15.3, and DeepSeek V4 Flash 0731 costs 6.3x less per output token ($0.396 vs $2.50 per million). Updated October 22, 2026; 8 benchmarks have a result for both.

Replace DeepSeek V4 Flash 0731 Replace Kimi K2 0905
DeepSeek V4 Flash 0731DeepSeek
Coding
51.8
Overall
55.2
Output $/M
$0.396
8
Kimi K2 0905Moonshot AI
Coding
No data
Overall
No data
Output $/M
$2.50
0
vs boards won of 8 shared

DeepSeek V4 Flash 0731 or Kimi K2 0905: which to pick

Only DeepSeek V4 Flash 0731 has a coding score, 51.8 on the Vibe Coding Index; Kimi K2 0905 has none, so the two cannot be ranked on coding.

Compare them on price, context and the boards below.

Model ADeepSeek V4 Flash 0731DeepSeek51.8/1004 independent benchmarks$0.01 per solved taskModel BKimi K2 0905Moonshot AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
8
DeepSeek V4 Flash 0731 only
47
Kimi K2 0905 only
9
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
DeepSeek V4 Flash 0731 51.8 from 4 benchmarks, Kimi K2 0905 not benchmarked.
Widest category
Coding, 30.5 points apart on average over 2 shared benchmarks.
Widest single gap
ALE-Bench: DeepSeek V4 Flash 0731 1306.1 against Kimi K2 0905 267.1, 34.6 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Flash 0731 $0.396 against Kimi K2 0905 $2.50 per million output tokens, 6.3x apart.
Context window
DeepSeek V4 Flash 0731 takes 1.05M tokens, Kimi K2 0905 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 V4 Flash 0731BarsKimi K2 0905Ties
Coding20
Intelligence10
Reasoning20
Web design20
General10
All shared boards80
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
Coding benchmarks for DeepSeek V4 Flash 0731 and Kimi K2 0905
BenchmarkDeepSeek V4 Flash 0731Kimi K2 0905Leader
AA Coding Index69.1Not measuredOnly DeepSeek V4 Flash 0731 measured
LiveCodeBench (Vals AI)87.3%Not measuredOnly DeepSeek V4 Flash 0731 measured
SWE-bench Verified (Vals AI)88.8%Not measuredOnly DeepSeek V4 Flash 0731 measured
Terminal-Bench 4 (Vals AI)18.7%Not measuredOnly DeepSeek V4 Flash 0731 measured
Vibe Code Bench (Vals AI)74.7%Not measuredOnly DeepSeek V4 Flash 0731 measured
Code migration (Vals AI)38.6%Not measuredOnly DeepSeek V4 Flash 0731 measured
ProgramBench (Vals AI)0.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
IOI (Vals AI)32.7%Not measuredOnly DeepSeek V4 Flash 0731 measured
Terminal-Bench 2.1 (Vals AI)67.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
SkillsBench (Vals AI)50.7%Not measuredOnly DeepSeek V4 Flash 0731 measured
CyberBench (Vals AI)72.1%Not measuredOnly DeepSeek V4 Flash 0731 measured
LiveCodeBench (Artificial Analysis run)Not measured61.0%Only Kimi K2 0905 measured
SciCode50.3%Not measuredOnly DeepSeek V4 Flash 0731 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured23.5%Only Kimi K2 0905 measured
FrontierCode18.8%Not measuredOnly DeepSeek V4 Flash 0731 measured
WeirdML63.0%36.7%DeepSeek V4 Flash 0731
ALE-Bench1306.1267.1DeepSeek V4 Flash 0731
Neither model has a result on the other 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for DeepSeek V4 Flash 0731 and Kimi K2 0905
BenchmarkDeepSeek V4 Flash 0731Kimi K2 0905Leader
AA Intelligence Index34.315.3DeepSeek V4 Flash 0731
Epoch Capabilities Index154.8Not measuredOnly DeepSeek V4 Flash 0731 measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Agentic work benchmarks for DeepSeek V4 Flash 0731 and Kimi K2 0905
BenchmarkDeepSeek V4 Flash 0731Kimi K2 0905Leader
AA Agentic Index41.0Not measuredOnly DeepSeek V4 Flash 0731 measured
Finance Agent (Vals AI)49.5%Not measuredOnly DeepSeek V4 Flash 0731 measured
Tax Agent Bench (Vals AI)28.1%Not measuredOnly DeepSeek V4 Flash 0731 measured
Legal Research Bench (Vals AI)30.3%Not measuredOnly DeepSeek V4 Flash 0731 measured
Excel Modeling Benchmark (Vals AI)57.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
BioMysteryBench (Vals AI)64.4%Not measuredOnly DeepSeek V4 Flash 0731 measured
Terminal-Bench-Science (Vals AI)4.3%Not measuredOnly DeepSeek V4 Flash 0731 measured
τ²-Bench TelecomNot measured73.4%Only Kimi K2 0905 measured
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
Reasoning benchmarks for DeepSeek V4 Flash 0731 and Kimi K2 0905
BenchmarkDeepSeek V4 Flash 0731Kimi K2 0905Leader
GPQA Diamond89.9%Not measuredOnly DeepSeek V4 Flash 0731 measured
GPQA Diamond (Artificial Analysis run)90.8%76.7%DeepSeek V4 Flash 0731
Humanity's Last Exam (Artificial Analysis run)38.6%6.4%DeepSeek V4 Flash 0731
GPQA Diamond (Epoch AI run)91.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
ARC-AGI89.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
ARC-AGI-261.4%Not measuredOnly DeepSeek V4 Flash 0731 measured
SimpleBench61.1%Not measuredOnly DeepSeek V4 Flash 0731 measured
Chess puzzles32.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
Mystery game puzzles34.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
Kagi LLM BenchmarkNot measured52.2%Only Kimi K2 0905 measured
Neither model has a result on the other 12 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Math benchmarks for DeepSeek V4 Flash 0731 and Kimi K2 0905
BenchmarkDeepSeek V4 Flash 0731Kimi K2 0905Leader
AA Math IndexNot measured57.3Only Kimi K2 0905 measured
AIME 2025 (Artificial Analysis run)Not measured57.3%Only Kimi K2 0905 measured
OTIS Mock AIME94.4%Not measuredOnly DeepSeek V4 Flash 0731 measured
FrontierMath, tiers 1 to 357.5%Not measuredOnly DeepSeek V4 Flash 0731 measured
FrontierMath, tier 424.4%Not measuredOnly DeepSeek V4 Flash 0731 measured
ProofBench56.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
Neither model has a result on the other 7 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Knowledge benchmarks for DeepSeek V4 Flash 0731 and Kimi K2 0905
BenchmarkDeepSeek V4 Flash 0731Kimi K2 0905Leader
MMLU Pro86.2%Not measuredOnly DeepSeek V4 Flash 0731 measured
LegalBench (Vals AI)77.7%Not measuredOnly DeepSeek V4 Flash 0731 measured
CorpFin (Vals AI)61.9%Not measuredOnly DeepSeek V4 Flash 0731 measured
TaxEval (Vals AI)70.7%Not measuredOnly DeepSeek V4 Flash 0731 measured
MedCode (Vals AI)41.4%Not measuredOnly DeepSeek V4 Flash 0731 measured
MMLU Pro (Artificial Analysis run)Not measured81.9%Only Kimi K2 0905 measured
SimpleQA Verified33.6%Not measuredOnly DeepSeek V4 Flash 0731 measured
Neither model has a result on the other 11 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index20
Web design benchmarks for DeepSeek V4 Flash 0731 and Kimi K2 0905
BenchmarkDeepSeek V4 Flash 0731Kimi K2 0905Leader
Design Arena: websites12371088DeepSeek V4 Flash 0731
Design Arena: UI components1233Not measuredOnly DeepSeek V4 Flash 0731 measured
Design Arena: game dev1207Not measuredOnly DeepSeek V4 Flash 0731 measured
Design Arena: data viz1180Not measuredOnly DeepSeek V4 Flash 0731 measured
Design Arena: 3D1208Not measuredOnly DeepSeek V4 Flash 0731 measured
Design Arena: all code categories12291098DeepSeek V4 Flash 0731
Design Arena: SVG1184Not measuredOnly DeepSeek V4 Flash 0731 measured
Design Arena: ASCII art1090Not measuredOnly DeepSeek V4 Flash 0731 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
General benchmarks for DeepSeek V4 Flash 0731 and Kimi K2 0905
BenchmarkDeepSeek V4 Flash 0731Kimi K2 0905Leader
MedScribe (Vals AI)80.4%Not measuredOnly DeepSeek V4 Flash 0731 measured
IFBenchNot measured41.7%Only Kimi K2 0905 measured
Long context reasoning (AA-LCR)79.7%53.0%DeepSeek V4 Flash 0731
DTBench90.9%Not measuredOnly DeepSeek V4 Flash 0731 measured
LMCA41.7%Not measuredOnly DeepSeek V4 Flash 0731 measured
Fiction.LiveBenchNot measured66.7%Only Kimi K2 0905 measured
Neither model has a result on the other 40 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V4 Flash 0731 and Kimi K2 0905
BenchmarkDeepSeek V4 Flash 0731Kimi K2 0905Leader
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 V4 Flash 0731$0.0003Fits in one request
Kimi K2 0905$0.0019Fits in one request

DeepSeek V4 Flash 0731 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Flash 0731$0.0082Fits in one request
Kimi K2 0905$0.037Fits in one request

DeepSeek V4 Flash 0731 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Flash 0731$0.032Fits in one request
Kimi K2 0905$0.145Fits in one request

DeepSeek V4 Flash 0731 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 V4 Flash 0731 and Kimi K2 0905
SpecificationDeepSeek V4 Flash 0731MoonshotAI Kimi K2 0905
MakerDeepSeekMoonshot AI
WeightsOpen weightsOpen weights
ReleasedJuly 31, 2026September 4, 2025
Context window1.05M262K
Input $/Mtok$0.14$0.60
Output $/Mtok$0.396$2.50
Coding index51.8Not benchmarked
Independent measurements behind it40
Cost per solved task$0.01Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Flash 0731 better than Kimi K2 0905 for coding?

Only DeepSeek V4 Flash 0731 has a coding score, 51.8 on the Vibe Coding Index; Kimi K2 0905 has none, so the two cannot be ranked on coding. Compare them on price, context and the boards below.

Which is cheaper, DeepSeek V4 Flash 0731 or Kimi K2 0905?

DeepSeek V4 Flash 0731 costs $0.14 per million input tokens and $0.396 per million output tokens; Kimi K2 0905 costs $0.60 and $2.50. Cost per solved task is known for DeepSeek V4 Flash 0731 only.

Which has the bigger context window, DeepSeek V4 Flash 0731 or Kimi K2 0905?

DeepSeek V4 Flash 0731, with 1.05M tokens against 262K.

How many benchmarks is the DeepSeek V4 Flash 0731 vs Kimi K2 0905 comparison based on?

8 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4 Flash 0731's coding index rests on 4 independent benchmarks and Kimi K2 0905's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next