Gemini 4 Carbon vs Kimi K2.5
Gemini 4 Carbon leads Kimi K2.5 on coding, 86.6 to 38.6 on the Vibe Coding Index, and Kimi K2.5 costs 3.5x less per output token ($2.85 vs $10.00 per million). Updated November 14, 2026; 43 benchmarks have a result for both.
vs boards won of 43 shared
Gemini 4 Carbon or Kimi K2.5: which to pick
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 38.6 for Kimi K2.5.
Pick Kimi K2.5 for output tokens 3.5x cheaper ($2.85 vs $10.00 per million).
Model AGemini 4 CarbonGoogle86.6/1004 independent benchmarksNo cost per solved taskModel BKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved task
- Shared results
- 43
- Gemini 4 Carbon only
- 30
- Kimi K2.5 only
- 66
- Like-for-like categories
- 8 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
Gemini 4 Carbon
Gemini 4 Carbon scores 86.6 against 38.6.
4 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only Gemini 4 Carbon has a AA Intelligence Index result, 60.0.
Directional only
Reasoning
GPQA Diamond
No call
Only Kimi K2.5 has a GPQA Diamond result, 84.1%.
Directional only
Math
AIME
No call
Only Kimi K2.5 has a AIME result, 95.6%.
Directional only
Knowledge
MMLU Pro
No call
Only Kimi K2.5 has a MMLU Pro result, 85.9%.
Directional only
Web design
Design Arena: websites
Gemini 4 Carbon
Gemini 4 Carbon leads, 1319 against 1241.
Same board, both measured
General
Vals Index
No call
Only Gemini 4 Carbon has a Vals Index result, 70.5%.
Directional only
Long documents
Listed context window
Gemini 4 Carbon
Gemini 4 Carbon takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Kimi K2.5
Gemini 4 Carbon $0.0070, Kimi K2.5 $0.0020 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Kimi K2.5 has the number, $0.24.
Directional only
At a glance
- Coding index
- Gemini 4 Carbon 86.6 from 4 benchmarks, Kimi K2.5 38.6 from 3 benchmarks.
- Widest category
- Agentic work, 50.2 points apart on average over 3 shared benchmarks.
- Widest single gap
- Vending-Bench 2: Gemini 4 Carbon $16,484 against Kimi K2.5 $1,198, 92.5 points apart on a 0 to 100 scale.
- Output price
- Gemini 4 Carbon $10.00 against Kimi K2.5 $2.85 per million output tokens, 3.5x apart.
- Context window
- Gemini 4 Carbon 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 | Gemini 4 Carbon | Bars | Kimi K2.5 | Ties |
|---|---|---|---|---|
| Coding | 7 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 3 | 0 | ||
| Reasoning | 6 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 6 | 0 | ||
| Web design | 5 | 0 | ||
| General | 13 | 0 | ||
| All shared boards | 43 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
| Benchmark | Gemini 4 Carbon | 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 |
| LiveBench coding | 91.0% | Not measured | Only Gemini 4 Carbon measured |
| LMArena WebDev | 1768 | 1436 | Gemini 4 Carbon |
| AA Coding Index | Not measured | 46.8 | Only Kimi K2.5 measured |
| LiveCodeBench (Vals AI) | Not measured | 83.9% | Only Kimi K2.5 measured |
| SWE-bench Verified (Vals AI) | Not measured | 70.0% | Only Kimi K2.5 measured |
| Terminal-Bench 4 (Vals AI) | 63.1% | Not measured | Only Gemini 4 Carbon measured |
| Vibe Code Bench (Vals AI) | 89.1% | 17.5% | Gemini 4 Carbon |
| Code migration (Vals AI) | Not measured | 7.0% | Only Kimi K2.5 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 42.0% | Only Kimi K2.5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 34.8% | Only Kimi K2.5 measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 65.2% | Not measured | Only Gemini 4 Carbon measured |
| FrontierCode 2.0 | 40.6% | Not measured | Only Gemini 4 Carbon measured |
| Terminal-Bench | Not measured | 43.2% | Only Kimi K2.5 measured |
| FrontierSWE | 61.2% | Not measured | Only Gemini 4 Carbon measured |
| WeirdML | Not measured | 45.6% | Only Kimi K2.5 measured |
| ALE-Bench | 2374.7 | 821.6 | Gemini 4 Carbon |
| LMArena Text: coding | 1564 | 1484 | Gemini 4 Carbon |
| LMArena Text: software and IT | 1552 | 1471 | Gemini 4 Carbon |
| LMArena WebDev: React | 1792 | 1428 | Gemini 4 Carbon |
| LMArena WebDev: HTML | 1770 | 1427 | Gemini 4 Carbon |
| LMArena WebDev: from an image | Not measured | 1439 | Only Kimi K2.5 measured |
| SWE Atlas: Codebase QnA | Not measured | 13.1% | Only Kimi K2.5 measured |
| SWE Atlas: Refactoring | Not measured | 20.9% | Only Kimi K2.5 measured |
| SWE Atlas: Test Writing | Not measured | 25.8% | Only Kimi K2.5 measured |
| Terminal-Bench 2.0 | Not measured | 43.2% | Only Kimi K2.5 measured |
| CursorBench 4.0 | 60.4% | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 24 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemini 4 Carbon | Kimi K2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 60.0 | Not measured | Only Gemini 4 Carbon measured |
| Epoch Capabilities Index | 169.8 | 148.8 | Gemini 4 Carbon |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Gemini 4 Carbon | Kimi K2.5 | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | Not measured | 1112 | Only Kimi K2.5 measured |
| Design Arena: agents building full-stack apps | Not measured | 1088 | Only Kimi K2.5 measured |
| Design Arena: agents building mobile apps | 1284 | 1139 | Gemini 4 Carbon |
| Design Arena: agents building Android apps | Not measured | 1105 | Only Kimi K2.5 measured |
| Design Arena: agents building Godot games | Not measured | 1219 | Only Kimi K2.5 measured |
| Design Arena: spreadsheets | 1224 | Not measured | Only Gemini 4 Carbon measured |
| LiveBench research | 92.5% | Not measured | Only Gemini 4 Carbon measured |
| LiveBench browser | 80.0% | Not measured | Only Gemini 4 Carbon measured |
| LiveBench long agentic | 72.7% | Not measured | Only Gemini 4 Carbon measured |
| Finance Agent (Vals AI) | Not measured | 35.8% | Only Kimi K2.5 measured |
| Tax Agent Bench (Vals AI) | 51.8% | Not measured | Only Gemini 4 Carbon measured |
| Legal Research Bench (Vals AI) | 55.8% | 15.9% | Gemini 4 Carbon |
| Harvey's Legal Agent Benchmark (Vals AI) | 17.5% | Not measured | Only Gemini 4 Carbon measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 28.5% | Only Kimi K2.5 measured |
| τ²-Bench Telecom | Not measured | 95.9% | Only Kimi K2.5 measured |
| APEX-Agents | 84.2% | Not measured | Only Gemini 4 Carbon measured |
| OSWorld | Not measured | 63.3% | Only Kimi K2.5 measured |
| Vending-Bench 2 | $16,484 | $1,198 | Gemini 4 Carbon |
| MCP Atlas | Not measured | 64.4% | Only Kimi K2.5 measured |
| Toolathlon-Verified | Not measured | 33.0% | Only Kimi K2.5 measured |
| Neither model has a result on the other 24 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Gemini 4 Carbon | Kimi K2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 84.1% | Only Kimi K2.5 measured |
| LiveBench reasoning | 90.6% | Not measured | Only Gemini 4 Carbon measured |
| MMMU Pro (Vals AI) | Not measured | 84.3% | Only Kimi K2.5 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 87.9% | Only Kimi K2.5 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 30.7% | Only Kimi K2.5 measured |
| HLE-Diamond (Artificial Analysis run) | 69.1% | Not measured | Only Gemini 4 Carbon measured |
| CritPt v2, hard subset (Artificial Analysis run) | 69.0% | Not measured | Only Gemini 4 Carbon measured |
| GPQA Diamond (Epoch AI run) | 96.5% | Not measured | Only Gemini 4 Carbon measured |
| ARC-AGI | 98.5% | 65.3% | Gemini 4 Carbon |
| ARC-AGI-2 | 94.2% | 11.8% | Gemini 4 Carbon |
| SimpleBench | 92.6% | 46.8% | Gemini 4 Carbon |
| Chess puzzles | 78.0% | Not measured | Only Gemini 4 Carbon measured |
| Mystery game puzzles | 73.0% | Not measured | Only Gemini 4 Carbon measured |
| EBR-bench | 87.6% | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: hard prompts | 1551 | 1453 | Gemini 4 Carbon |
| LMArena Text: expert | 1582 | 1465 | Gemini 4 Carbon |
| LMArena Text: hard prompts in English | 1545 | 1460 | Gemini 4 Carbon |
| LMArena Vision: diagrams | Not measured | 1282 | Only Kimi K2.5 measured |
| LMArena Vision: homework | Not measured | 1296 | Only Kimi K2.5 measured |
| Kagi LLM Benchmark | Not measured | 78.5% | 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 index20
| Benchmark | Gemini 4 Carbon | Kimi K2.5 | Leader |
|---|---|---|---|
| AIME | Not measured | 95.6% | Only Kimi K2.5 measured |
| OTIS Mock AIME | 100.0% | Not measured | Only Gemini 4 Carbon measured |
| FrontierMath, tiers 1 to 3 | 90.5% | Not measured | Only Gemini 4 Carbon measured |
| FrontierMath, tier 4 | 95.1% | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: math | Not measured | 1469 | Only Kimi K2.5 measured |
| LMArena Text: mathematical work | 1538 | 1473 | Gemini 4 Carbon |
| MathArena | 85.4% | 17.5% | Gemini 4 Carbon |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Gemini 4 Carbon | Kimi K2.5 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 85.9% | Only Kimi K2.5 measured |
| CaseLaw (Vals AI) | Not measured | 58.7% | Only Kimi K2.5 measured |
| CorpFin (Vals AI) | Not measured | 68.3% | Only Kimi K2.5 measured |
| TaxEval (Vals AI) | Not measured | 74.2% | Only Kimi K2.5 measured |
| 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) | Not measured | 39.3% | Only Kimi K2.5 measured |
| AA-Omniscience | 53.5 | Not measured | Only Gemini 4 Carbon measured |
| SimpleQA Verified | 77.7% | 34.3% | Gemini 4 Carbon |
| LMArena Text: science | 1535 | 1458 | Gemini 4 Carbon |
| LMArena Text: medicine and healthcare | 1525 | 1449 | Gemini 4 Carbon |
| LMArena Text: legal and government | 1542 | 1441 | Gemini 4 Carbon |
| LMArena Text: business and finance | 1520 | 1427 | Gemini 4 Carbon |
| FACTS Benchmark Suite | 78.4% | Not measured | Only Gemini 4 Carbon measured |
| PRBench Finance | Not measured | 46.5% | Only Kimi K2.5 measured |
| PRBench Legal | 53.3% | 43.8% | Gemini 4 Carbon |
| Neither model has a result on the other 5 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Gemini 4 Carbon | Kimi K2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1319 | 1241 | Gemini 4 Carbon |
| Design Arena: UI components | 1357 | 1227 | Gemini 4 Carbon |
| Design Arena: game dev | 1326 | 1196 | Gemini 4 Carbon |
| Design Arena: data viz | Not measured | 1216 | Only Kimi K2.5 measured |
| Design Arena: 3D | 1434 | 1185 | Gemini 4 Carbon |
| Design Arena: all code categories | 1348 | 1226 | Gemini 4 Carbon |
| Design Arena: SVG | Not measured | 1139 | Only Kimi K2.5 measured |
| Design Arena: ASCII art | Not measured | 1160 | Only Kimi K2.5 measured |
| LiveBench design | 80.2% | Not measured | Only Gemini 4 Carbon measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index130
| Benchmark | Gemini 4 Carbon | Kimi K2.5 | Leader |
|---|---|---|---|
| Vals Index | 70.5% | Not measured | Only Gemini 4 Carbon measured |
| LiveBench data analysis | 86.5% | Not measured | Only Gemini 4 Carbon measured |
| MedScribe (Vals AI) | Not measured | 76.4% | Only Kimi K2.5 measured |
| IFBench | Not measured | 70.2% | Only Kimi K2.5 measured |
| Long context reasoning (AA-LCR) | 79.3% | 78.0% | Gemini 4 Carbon |
| GDPval-AA | 1733 | 847 | Gemini 4 Carbon |
| Fiction.LiveBench | Not measured | 86.1% | Only Kimi K2.5 measured |
| CL-bench | Not measured | 19.3% | Only Kimi K2.5 measured |
| Furniture assembly | 77.5% | Not measured | Only Gemini 4 Carbon measured |
| CL-bench Life | Not measured | 13.2% | Only Kimi K2.5 measured |
| LMArena Text | 1538 | 1445 | Gemini 4 Carbon |
| LMArena Text: instruction following | 1539 | 1431 | Gemini 4 Carbon |
| LMArena Text: creative writing | 1533 | 1422 | Gemini 4 Carbon |
| LMArena Vision | Not measured | 1269 | Only Kimi K2.5 measured |
| LMArena Text: English | 1530 | 1453 | Gemini 4 Carbon |
| LMArena Text: non-English | 1534 | 1432 | Gemini 4 Carbon |
| LMArena Text: Chinese | 1613 | 1493 | Gemini 4 Carbon |
| LMArena Text: German | Not measured | 1441 | Only Kimi K2.5 measured |
| LMArena Text: Japanese | Not measured | 1422 | Only Kimi K2.5 measured |
| LMArena Text: Korean | Not measured | 1410 | Only Kimi K2.5 measured |
| LMArena Text: French | Not measured | 1454 | Only Kimi K2.5 measured |
| LMArena Text: Spanish | Not measured | 1449 | Only Kimi K2.5 measured |
| LMArena Text: Russian | 1560 | 1435 | Gemini 4 Carbon |
| LMArena Text: Polish | Not measured | 1445 | Only Kimi K2.5 measured |
| LMArena Text: multi-turn | 1569 | 1444 | Gemini 4 Carbon |
| LMArena Text: longer queries | 1549 | 1444 | Gemini 4 Carbon |
| LMArena Text: writing and language | 1542 | 1425 | Gemini 4 Carbon |
| LMArena Text: entertainment and media | 1527 | 1417 | Gemini 4 Carbon |
| LMArena Vision: English | Not measured | 1274 | Only Kimi K2.5 measured |
| LMArena Vision: Chinese | Not measured | 1327 | 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 | 1250 | Only Kimi K2.5 measured |
| LMArena Vision: recognizing things | Not measured | 1287 | Only Kimi K2.5 measured |
| LMArena Vision: creative writing | Not measured | 1270 | Only Kimi K2.5 measured |
| LMArena Document | Not measured | 1431 | Only Kimi K2.5 measured |
| MultiChallenge | Not measured | 61.4% | Only Kimi K2.5 measured |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 4 Carbon | 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
Gemini 4 Carbon$0.0070Fits in one request
Kimi K2.5$0.0020Fits in one request
Kimi K2.5 costs less
Repository review
50K input + 3K output tokens
Gemini 4 Carbon$0.130Fits in one request
Kimi K2.5$0.035Fits in one request
Kimi K2.5 costs less
Agent loop
200K input + 10K output tokens
Gemini 4 Carbon$0.500Fits in one request
Kimi K2.5$0.135Fits in one request
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 | Google Gemini 4 Carbon | MoonshotAI Kimi K2.5 |
|---|---|---|
| Maker | Moonshot AI | |
| Weights | No public weights listed | Open weights |
| Released | November 10, 2026 | January 27, 2026 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $2.00 | $0.532 |
| Output $/Mtok | $10.00 | $2.85 |
| Coding index | 86.6 | 38.6 |
| Independent measurements behind it | 4 | 3 |
| Cost per solved task | Not computable | $0.24 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 4 Carbon better than Kimi K2.5 for coding?
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 38.6 for Kimi K2.5. Pick Kimi K2.5 for output tokens 3.5x cheaper ($2.85 vs $10.00 per million).
Which is cheaper, Gemini 4 Carbon or Kimi K2.5?
Gemini 4 Carbon costs $2.00 per million input tokens and $10.00 per million output tokens; Kimi K2.5 costs $0.532 and $2.85. Cost per solved task is known for Kimi K2.5 only.
Which has the bigger context window, Gemini 4 Carbon or Kimi K2.5?
Gemini 4 Carbon, with 1.05M tokens against 262K.
How many benchmarks is the Gemini 4 Carbon vs Kimi K2.5 comparison based on?
43 benchmarks have a result for both models as of November 14, 2026. Gemini 4 Carbon's coding index rests on 4 independent benchmarks and Kimi K2.5's on 3. Where only one model has a result, the page says so instead of naming a winner.