DeepSeek V3 0324 vs Kimi K2 Thinking
Kimi K2 Thinking leads DeepSeek V3 0324 on the Artificial Analysis Intelligence Index, 22.0 to 9.7, and DeepSeek V3 0324 costs 2.3x less per output token ($1.07 vs $2.50 per million). Updated October 22, 2026; 23 benchmarks have a result for both.
DeepSeek V3 0324 or Kimi K2 Thinking: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick DeepSeek V3 0324 for output tokens 2.3x cheaper ($1.07 vs $2.50 per million) and work measured by SWE-bench Verified or LiveCodeBench (Artificial Analysis run), where it leads.
- Shared results
- 23
- DeepSeek V3 0324 only
- 12
- Kimi K2 Thinking only
- 7
- 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.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Kimi K2 Thinking
Kimi K2 Thinking leads, 22.0 against 9.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V3 0324 has a AA Agentic Index result, 0.8.
Directional only
Reasoning
GPQA Diamond
Kimi K2 Thinking
Kimi K2 Thinking leads, 78.5% against 61.6%.
Same board, both measured
Math
AIME
Kimi K2 Thinking
Kimi K2 Thinking leads, 85.4% against 52.2%.
Same board, both measured
Knowledge
MMLU Pro
Kimi K2 Thinking
Kimi K2 Thinking leads, 81.1% against 79.5%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Kimi K2 Thinking has a Design Arena: websites result, 1113.
Directional only
Long documents
Listed context window
Kimi K2 Thinking
Kimi K2 Thinking takes 262K tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3 0324
DeepSeek V3 0324 $0.0008, Kimi K2 Thinking $0.0019 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Kimi K2 Thinking has the number, $0.61.
Directional only
At a glance
- Coding index
- DeepSeek V3 0324 not benchmarked, Kimi K2 Thinking not benchmarked.
- Widest category
- Math, 35.5 points apart on average over 4 shared benchmarks.
- Widest single gap
- AA Math Index: DeepSeek V3 0324 41.0 against Kimi K2 Thinking 94.7, 53.7 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3 0324 $1.07 against Kimi K2 Thinking $2.50 per million output tokens, 2.3x apart.
- Context window
- DeepSeek V3 0324 takes 164K 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.
| Category | DeepSeek V3 0324 | Bars | Kimi K2 Thinking | Ties |
|---|---|---|---|---|
| Coding | 1 | 4 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 2 | ||
| Reasoning | 0 | 3 | ||
| Math | 1 | 3 | ||
| Knowledge | 0 | 6 | ||
| General | 0 | 2 | ||
| All shared boards | 2 | 21 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index14
| Benchmark | DeepSeek V3 0324 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| SWE-bench Verified | 42.0% | 63.4% | Kimi K2 Thinking |
| AA Coding Index | 21.2 | Not measured | Only DeepSeek V3 0324 measured |
| LiveCodeBench (Vals AI) | 65.5% | 63.1% | DeepSeek V3 0324 |
| SWE-bench Verified (Vals AI) | Not measured | 60.2% | Only Kimi K2 Thinking measured |
| LiveCodeBench (Artificial Analysis run) | 40.5% | 85.3% | Kimi K2 Thinking |
| SciCode | 39.0% | Not measured | Only DeepSeek V3 0324 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 15.2% | 31.1% | Kimi K2 Thinking |
| Terminal-Bench | Not measured | 35.7% | Only Kimi K2 Thinking measured |
| WeirdML | 36.1% | 42.8% | Kimi K2 Thinking |
| ALE-Bench | Not measured | 597.5 | Only Kimi K2 Thinking measured |
| Neither model has a result on the other 29 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3 0324 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AA Intelligence Index | 9.7 | 22.0 | Kimi K2 Thinking |
| Epoch Capabilities Index | Not measured | 145.8 | Only Kimi K2 Thinking measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V3 0324 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AA Agentic Index | 0.8 | Not measured | Only DeepSeek V3 0324 measured |
| τ²-Bench Telecom | 47.1% | 93.0% | Kimi K2 Thinking |
| METR time horizons | 49.6% | 59.2% | Kimi K2 Thinking |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | DeepSeek V3 0324 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| GPQA Diamond | 61.6% | 78.5% | Kimi K2 Thinking |
| GPQA Diamond (Artificial Analysis run) | 65.5% | 83.8% | Kimi K2 Thinking |
| Humanity's Last Exam (Artificial Analysis run) | 4.7% | 23.8% | Kimi K2 Thinking |
| GPQA Diamond (Epoch AI run) | 67.6% | Not measured | Only DeepSeek V3 0324 measured |
| SimpleBench | 27.2% | Not measured | Only DeepSeek V3 0324 measured |
| Neither model has a result on the other 17 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | DeepSeek V3 0324 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AIME | 52.2% | 85.4% | Kimi K2 Thinking |
| MATH 500 (Vals AI) | 88.6% | Not measured | Only DeepSeek V3 0324 measured |
| MGSM (Vals AI) | 91.7% | 90.2% | DeepSeek V3 0324 |
| AA Math Index | 41.0 | 94.7 | Kimi K2 Thinking |
| AIME 2025 (Artificial Analysis run) | 41.0% | 94.7% | Kimi K2 Thinking |
| OTIS Mock AIME | 37.8% | Not measured | Only DeepSeek V3 0324 measured |
| MATH level 5 | 75.5% | Not measured | Only DeepSeek V3 0324 measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | DeepSeek V3 0324 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| MMLU Pro | 79.5% | 81.1% | Kimi K2 Thinking |
| LegalBench (Vals AI) | 77.7% | 80.2% | Kimi K2 Thinking |
| CaseLaw (Vals AI) | Not measured | 65.7% | Only Kimi K2 Thinking measured |
| CorpFin (Vals AI) | 54.7% | 60.6% | Kimi K2 Thinking |
| TaxEval (Vals AI) | 71.1% | 71.7% | Kimi K2 Thinking |
| MedQA (Vals AI) | 82.0% | 92.6% | Kimi K2 Thinking |
| MMLU Pro (Artificial Analysis run) | 81.9% | 84.8% | Kimi K2 Thinking |
| Neither model has a result on the other 11 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | DeepSeek V3 0324 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1113 | Only Kimi K2 Thinking measured |
| Neither model has a result on the other 8 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V3 0324 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| IFBench | 41.0% | 68.1% | Kimi K2 Thinking |
| Long context reasoning (AA-LCR) | 40.7% | 72.0% | Kimi K2 Thinking |
| DTBench | 64.8% | Not measured | Only DeepSeek V3 0324 measured |
| LMCA | 15.5% | Not measured | Only DeepSeek V3 0324 measured |
| Fiction.LiveBench | 50.0% | Not measured | Only DeepSeek V3 0324 measured |
| Creative writing (Lech Mazur) | 77.0% | Not measured | Only DeepSeek V3 0324 measured |
| CL-bench | Not measured | 17.6% | Only Kimi K2 Thinking measured |
| Neither model has a result on the other 39 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3 0324 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| 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 0324 costs less
Repository review
50K input + 3K output tokens
DeepSeek V3 0324 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3 0324 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.
| Specification | DeepSeek V3 0324 | MoonshotAI Kimi K2 Thinking |
|---|---|---|
| Maker | DeepSeek | Moonshot AI |
| Weights | Open weights | Open weights |
| Released | March 24, 2025 | November 6, 2025 |
| Context window | 164K | 262K |
| Input $/Mtok | $0.27 | $0.60 |
| Output $/Mtok | $1.07 | $2.50 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | $0.61 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3 0324 better than Kimi K2 Thinking for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3 0324 for output tokens 2.3x cheaper ($1.07 vs $2.50 per million) and work measured by SWE-bench Verified or LiveCodeBench (Artificial Analysis run), where it leads.
Which is cheaper, DeepSeek V3 0324 or Kimi K2 Thinking?
DeepSeek V3 0324 costs $0.27 per million input tokens and $1.07 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, DeepSeek V3 0324 or Kimi K2 Thinking?
Kimi K2 Thinking, with 262K tokens against 164K.
How many benchmarks is the DeepSeek V3 0324 vs Kimi K2 Thinking comparison based on?
23 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3 0324'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.