DeepSeek V4 Pro 0813 vs Kimi K2.5
Updated October 21, 2026. 53 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Kimi K2.5 for coding: it scores 58.5 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813.
Pick DeepSeek V4 Pro 0813 when output tokens cost 1.3x less, or when a solved task costs $0.10 against $0.24.
- Shared results
- 53
- DeepSeek V4 Pro 0813 only
- 25
- Kimi K2.5 only
- 45
- Like-for-like categories
- 7 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.
Coding
Vibe Coding Index, four public coding benchmarks
Kimi K2.5
Kimi K2.5 scores 58.5 against 54.6.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 leads, 36.0 against 23.5.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V4 Pro 0813 has a AA Agentic Index result, 41.3.
Directional only
Reasoning
GPQA Diamond
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 leads, 92.4% against 84.1%.
Same board, both measured
Math
AIME
No call
Only Kimi K2.5 has a AIME result, 95.6%.
Directional only
Knowledge
MMLU Pro
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 leads, 87.0% against 85.9%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Kimi K2.5 has a Design Arena: websites result, 1249.
Directional only
General
Vals Index
No call
Only DeepSeek V4 Pro 0813 has a Vals Index result, 53.0%.
Directional only
Long documents
Listed context window
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 $0.0016, Kimi K2.5 $0.0018 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 $0.10, Kimi K2.5 $0.24.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V4 Pro 0813 54.6 from 1 benchmark, Kimi K2.5 58.5 from 2 benchmarks.
- Widest category
- Coding, 21.4 points apart on average over 13 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): DeepSeek V4 Pro 0813 82.3% against Kimi K2.5 17.5%, 64.8 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Pro 0813 $1.98 against Kimi K2.5 $2.50 per million output tokens, 1.3x apart.
- Context window
- DeepSeek V4 Pro 0813 takes 1.05M 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.
| Category | DeepSeek V4 Pro 0813 | Bars | Kimi K2.5 | Ties |
|---|---|---|---|---|
| Coding | 11 | 2 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 3 | 0 | ||
| Reasoning | 7 | 1 | ||
| Math | 0 | 2 | ||
| Knowledge | 5 | 4 | ||
| General | 12 | 4 | ||
| All shared boards | 40 | 13 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index112
| Benchmark | DeepSeek V4 Pro 0813 | Kimi K2.5 | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 70.8% | Only Kimi K2.5 measured |
| SWE-bench Multilingual | Not measured | 67.3% | Only Kimi K2.5 measured |
| LMArena WebDev | 1582 | 1437 | DeepSeek V4 Pro 0813 |
| AA Coding Index | 68.8 | 46.8 | DeepSeek V4 Pro 0813 |
| LiveCodeBench (Vals AI) | 87.5% | 83.9% | DeepSeek V4 Pro 0813 |
| SWE-bench Verified (Vals AI) | 96.4% | 70.0% | DeepSeek V4 Pro 0813 |
| Terminal-Bench 4 (Vals AI) | 14.1% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Vibe Code Bench (Vals AI) | 82.3% | 17.5% | DeepSeek V4 Pro 0813 |
| Code migration (Vals AI) | 41.5% | 7.0% | DeepSeek V4 Pro 0813 |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| IOI (Vals AI) | 51.6% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Terminal-Bench 2.1 (Vals AI) | 54.7% | 42.0% | DeepSeek V4 Pro 0813 |
| Vibe Code Bench 1-100 (Vals AI) | 17.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| SkillsBench (Vals AI) | 53.8% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| CyberBench (Vals AI) | 72.9% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| SciCode | 51.0% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 34.8% | Only Kimi K2.5 measured |
| Terminal-Bench | Not measured | 43.2% | Only Kimi K2.5 measured |
| FrontierCode | 28.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| WeirdML | 66.2% | 45.6% | DeepSeek V4 Pro 0813 |
| ALE-Bench | 1403.2 | 821.6 | DeepSeek V4 Pro 0813 |
| LMArena Text: coding | 1469 | 1483 | Kimi K2.5 |
| LMArena Text: software and IT | 1462 | 1471 | Kimi K2.5 |
| LMArena WebDev: React | 1588 | 1429 | DeepSeek V4 Pro 0813 |
| LMArena WebDev: HTML | 1566 | 1426 | DeepSeek V4 Pro 0813 |
| LMArena WebDev: from an image | Not measured | 1439 | Only Kimi K2.5 measured |
| Neither model has a result on the other 12 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | DeepSeek V4 Pro 0813 | Kimi K2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 36.0 | 23.5 | DeepSeek V4 Pro 0813 |
| Epoch Capabilities Index | 155.6 | 148.1 | DeepSeek V4 Pro 0813 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | DeepSeek V4 Pro 0813 | Kimi K2.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 41.3 | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Design Arena: agents building web apps | Not measured | 1136 | Only Kimi K2.5 measured |
| Design Arena: agents building full-stack apps | Not measured | 1114 | Only Kimi K2.5 measured |
| Design Arena: agents building mobile apps | Not measured | 1147 | Only Kimi K2.5 measured |
| Design Arena: agents building Android apps | Not measured | 1124 | Only Kimi K2.5 measured |
| Design Arena: agents building Godot games | Not measured | 1219 | Only Kimi K2.5 measured |
| SREBench (Vals AI) | 1.9% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Finance Agent (Vals AI) | 50.4% | 35.8% | DeepSeek V4 Pro 0813 |
| Tax Agent Bench (Vals AI) | 26.8% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Legal Research Bench (Vals AI) | 40.9% | 15.9% | DeepSeek V4 Pro 0813 |
| Harvey's Legal Agent Benchmark (Vals AI) | 10.8% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Excel Modeling Benchmark (Vals AI) | 52.8% | 28.5% | DeepSeek V4 Pro 0813 |
| Terminal-Bench-Science (Vals AI) | 4.3% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| τ²-Bench Telecom | Not measured | 95.9% | Only Kimi K2.5 measured |
| APEX-Agents | 47.3% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| OSWorld | Not measured | 63.3% | Only Kimi K2.5 measured |
| Vending-Bench 2 | Not measured | $1,198 | Only Kimi K2.5 measured |
| Neither model has a result on the other 22 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index71
| Benchmark | DeepSeek V4 Pro 0813 | Kimi K2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 92.4% | 84.1% | DeepSeek V4 Pro 0813 |
| MMMU Pro (Vals AI) | Not measured | 84.3% | Only Kimi K2.5 measured |
| GPQA Diamond (Artificial Analysis run) | 92.8% | 87.9% | DeepSeek V4 Pro 0813 |
| Humanity's Last Exam (Artificial Analysis run) | 41.0% | 30.7% | DeepSeek V4 Pro 0813 |
| GPQA Diamond (Epoch AI run) | 91.7% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| ARC-AGI | 90.5% | 65.3% | DeepSeek V4 Pro 0813 |
| ARC-AGI-2 | 61.3% | 11.8% | DeepSeek V4 Pro 0813 |
| SimpleBench | Not measured | 46.8% | Only Kimi K2.5 measured |
| Chess puzzles | 46.0% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Mystery game puzzles | 43.0% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LMArena Text: hard prompts | 1458 | 1453 | DeepSeek V4 Pro 0813 |
| LMArena Text: expert | 1459 | 1466 | Kimi K2.5 |
| LMArena Text: hard prompts in English | 1463 | 1460 | DeepSeek V4 Pro 0813 |
| LMArena Vision: diagrams | Not measured | 1282 | Only Kimi K2.5 measured |
| LMArena Vision: homework | Not measured | 1297 | Only Kimi K2.5 measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V4 Pro 0813 | Kimi K2.5 | Leader |
|---|---|---|---|
| AIME | Not measured | 95.6% | Only Kimi K2.5 measured |
| OTIS Mock AIME | 98.6% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| FrontierMath, tiers 1 to 3 | 64.6% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| FrontierMath, tier 4 | 26.8% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| ProofBench | 50.0% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LMArena Text: math | 1441 | 1470 | Kimi K2.5 |
| LMArena Text: mathematical work | 1443 | 1473 | Kimi K2.5 |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index54
| Benchmark | DeepSeek V4 Pro 0813 | Kimi K2.5 | Leader |
|---|---|---|---|
| MMLU Pro | 87.0% | 85.9% | DeepSeek V4 Pro 0813 |
| LegalBench (Vals AI) | 82.4% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| CaseLaw (Vals AI) | Not measured | 58.7% | Only Kimi K2.5 measured |
| CorpFin (Vals AI) | 65.4% | 68.3% | Kimi K2.5 |
| TaxEval (Vals AI) | 73.1% | 74.2% | Kimi K2.5 |
| MortgageTax (Vals AI) | Not measured | 66.5% | Only Kimi K2.5 measured |
| MedQA (Vals AI) | Not measured | 94.4% | Only Kimi K2.5 measured |
| MedCode (Vals AI) | 42.5% | 39.3% | DeepSeek V4 Pro 0813 |
| SimpleQA Verified | 52.9% | 34.3% | DeepSeek V4 Pro 0813 |
| LMArena Text: science | 1457 | 1459 | Kimi K2.5 |
| LMArena Text: medicine and healthcare | 1446 | 1448 | Kimi K2.5 |
| LMArena Text: legal and government | 1459 | 1441 | DeepSeek V4 Pro 0813 |
| LMArena Text: business and finance | 1442 | 1427 | DeepSeek V4 Pro 0813 |
| Neither model has a result on the other 4 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | DeepSeek V4 Pro 0813 | Kimi K2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1249 | Only Kimi K2.5 measured |
| Design Arena: UI components | Not measured | 1236 | Only Kimi K2.5 measured |
| Design Arena: game dev | Not measured | 1207 | Only Kimi K2.5 measured |
| Design Arena: data viz | Not measured | 1219 | Only Kimi K2.5 measured |
| Design Arena: 3D | Not measured | 1205 | Only Kimi K2.5 measured |
| Design Arena: all code categories | Not measured | 1236 | Only Kimi K2.5 measured |
| Design Arena: SVG | Not measured | 1149 | Only Kimi K2.5 measured |
| Design Arena: ASCII art | Not measured | 1165 | Only 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 index124
| Benchmark | DeepSeek V4 Pro 0813 | Kimi K2.5 | Leader |
|---|---|---|---|
| Vals Index | 53.0% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| SAGE (Vals AI) | Not measured | 49.9% | Only Kimi K2.5 measured |
| MedScribe (Vals AI) | 80.2% | 76.4% | DeepSeek V4 Pro 0813 |
| IFBench | Not measured | 70.2% | Only Kimi K2.5 measured |
| Long context reasoning (AA-LCR) | 80.3% | 78.0% | DeepSeek V4 Pro 0813 |
| DTBench | 93.9% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LMCA | 45.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Fiction.LiveBench | Not measured | 86.1% | Only Kimi K2.5 measured |
| CL-bench | Not measured | 19.3% | Only Kimi K2.5 measured |
| CL-bench Life | Not measured | 13.2% | Only Kimi K2.5 measured |
| LMArena Text | 1446 | 1445 | DeepSeek V4 Pro 0813 |
| LMArena Text: instruction following | 1448 | 1431 | DeepSeek V4 Pro 0813 |
| LMArena Text: creative writing | 1439 | 1422 | DeepSeek V4 Pro 0813 |
| LMArena Vision | Not measured | 1269 | Only Kimi K2.5 measured |
| LMArena Text: English | 1457 | 1453 | DeepSeek V4 Pro 0813 |
| LMArena Text: non-English | 1431 | 1433 | Kimi K2.5 |
| LMArena Text: Chinese | 1481 | 1494 | Kimi K2.5 |
| LMArena Text: German | Not measured | 1441 | Only Kimi K2.5 measured |
| LMArena Text: Japanese | Not measured | 1423 | Only Kimi K2.5 measured |
| LMArena Text: Korean | 1449 | 1412 | DeepSeek V4 Pro 0813 |
| LMArena Text: French | 1446 | 1454 | Kimi K2.5 |
| LMArena Text: Spanish | 1435 | 1450 | Kimi K2.5 |
| LMArena Text: Russian | 1448 | 1435 | DeepSeek V4 Pro 0813 |
| LMArena Text: Polish | Not measured | 1445 | Only Kimi K2.5 measured |
| LMArena Text: multi-turn | 1454 | 1444 | DeepSeek V4 Pro 0813 |
| LMArena Text: longer queries | 1458 | 1445 | DeepSeek V4 Pro 0813 |
| LMArena Text: writing and language | 1443 | 1425 | DeepSeek V4 Pro 0813 |
| LMArena Text: entertainment and media | 1424 | 1417 | DeepSeek V4 Pro 0813 |
| LMArena Vision: English | Not measured | 1274 | Only Kimi K2.5 measured |
| LMArena Vision: Chinese | Not measured | 1328 | Only Kimi K2.5 measured |
| LMArena Vision: reading text | Not measured | 1276 | Only Kimi K2.5 measured |
| LMArena Vision: humor | Not measured | 1284 | Only Kimi K2.5 measured |
| LMArena Vision: captioning | Not measured | 1257 | Only Kimi K2.5 measured |
| LMArena Vision: recognizing things | Not measured | 1285 | Only Kimi K2.5 measured |
| LMArena Vision: creative writing | Not measured | 1269 | Only Kimi K2.5 measured |
| 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
| Benchmark | DeepSeek V4 Pro 0813 | Kimi K2.5 | 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 V4 Pro 0813 costs less
Repository review
50K input + 3K output tokens
Kimi K2.5 costs less
Agent loop
200K input + 10K output tokens
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.
| Specification | DeepSeek V4 Pro 0813 | MoonshotAI Kimi K2.5 |
|---|---|---|
| Maker | DeepSeek | Moonshot AI |
| Weights | Open weights | Open weights |
| Released | August 12, 2026 | January 27, 2026 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $0.66 | $0.50 |
| Output $/Mtok | $1.98 | $2.50 |
| Coding index | 54.6 | 58.5 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | $0.10 | $0.24 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Pro 0813 better than Kimi K2.5 for coding?
Pick Kimi K2.5 for coding: it scores 58.5 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813. Pick DeepSeek V4 Pro 0813 when output tokens cost 1.3x less, or when a solved task costs $0.10 against $0.24.
Which is cheaper, DeepSeek V4 Pro 0813 or Kimi K2.5?
DeepSeek V4 Pro 0813 costs $0.66 per million input tokens and $1.98 per million output tokens; Kimi K2.5 costs $0.50 and $2.50. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0813 costs $0.10 and Kimi K2.5 $0.24.
Which has the bigger context window, DeepSeek V4 Pro 0813 or Kimi K2.5?
DeepSeek V4 Pro 0813, with 1.05M tokens against 262K.
How many benchmarks is the DeepSeek V4 Pro 0813 vs Kimi K2.5 comparison based on?
53 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Pro 0813's coding index rests on 1 independent benchmark and Kimi K2.5's on 2. Where only one model has a result, the page says so instead of naming a winner.