Kimi K2.5 vs Hy3
Updated October 21, 2026. 43 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 43.9 for Hy3.
Pick Hy3 when output tokens cost 4.7x less, or when what matters is LMArena WebDev or ALE-Bench, where it leads.
- Shared results
- 43
- Kimi K2.5 only
- 55
- Hy3 only
- 1
- Like-for-like categories
- 6 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 43.9.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only Kimi K2.5 has a AA Intelligence Index result, 23.5.
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
Kimi K2.5
Kimi K2.5 leads, 1249 against 1230.
Same board, both measured
Long documents
Listed context window
No call
Both take 262K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy3
Kimi K2.5 $0.0018, Hy3 $0.0004 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
- Kimi K2.5 58.5 from 2 benchmarks, Hy3 43.9 from 1 benchmark.
- Widest category
- Coding, 6.4 points apart on average over 6 shared benchmarks.
- Widest single gap
- LMArena WebDev: React: Kimi K2.5 1429 against Hy3 1511, 13.6 points apart on a 0 to 100 scale.
- Output price
- Kimi K2.5 $2.50 against Hy3 $0.528 per million output tokens, 4.7x apart.
- Context window
- Both take 262K tokens.
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 | Kimi K2.5 | Bars | Hy3 | Ties |
|---|---|---|---|---|
| Coding | 2 | 4 | ||
| Reasoning | 3 | 2 | ||
| Math | 0 | 2 | ||
| Knowledge | 3 | 1 | ||
| Web design | 5 | 3 | ||
| General | 13 | 5 | ||
| All shared boards | 26 | 17 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index24
| Benchmark | Kimi K2.5 | Hy3 | Leader |
|---|---|---|---|
| SWE-bench Verified | 70.8% | Not measured | Only Kimi K2.5 measured |
| SWE-bench Multilingual | 67.3% | Not measured | Only Kimi K2.5 measured |
| LMArena WebDev | 1437 | 1507 | Hy3 |
| AA Coding Index | 46.8 | Not measured | Only Kimi K2.5 measured |
| LiveCodeBench (Vals AI) | 83.9% | Not measured | Only Kimi K2.5 measured |
| SWE-bench Verified (Vals AI) | 70.0% | Not measured | Only Kimi K2.5 measured |
| Vibe Code Bench (Vals AI) | 17.5% | Not measured | Only Kimi K2.5 measured |
| Code migration (Vals AI) | 7.0% | Not measured | Only Kimi K2.5 measured |
| Terminal-Bench 2.1 (Vals AI) | 42.0% | Not measured | Only Kimi K2.5 measured |
| SciCode | Not measured | 48.6% | Only Hy3 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 34.8% | Not measured | Only Kimi K2.5 measured |
| Terminal-Bench | 43.2% | Not measured | Only Kimi K2.5 measured |
| WeirdML | 45.6% | Not measured | Only Kimi K2.5 measured |
| ALE-Bench | 821.6 | 838.6 | Hy3 |
| LMArena Text: coding | 1483 | 1466 | Kimi K2.5 |
| LMArena Text: software and IT | 1471 | 1463 | Kimi K2.5 |
| LMArena WebDev: React | 1429 | 1511 | Hy3 |
| LMArena WebDev: HTML | 1426 | 1487 | Hy3 |
| LMArena WebDev: from an image | 1439 | Not measured | Only Kimi K2.5 measured |
| Neither model has a result on the other 19 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Kimi K2.5 | Hy3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 23.5 | Not measured | Only Kimi K2.5 measured |
| Epoch Capabilities Index | 148.1 | Not measured | Only Kimi K2.5 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | Kimi K2.5 | Hy3 | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1136 | Not measured | Only Kimi K2.5 measured |
| Design Arena: agents building full-stack apps | 1114 | Not measured | Only Kimi K2.5 measured |
| Design Arena: agents building mobile apps | 1147 | Not measured | Only Kimi K2.5 measured |
| Design Arena: agents building Android apps | 1124 | Not measured | Only Kimi K2.5 measured |
| Design Arena: agents building Godot games | 1219 | Not measured | Only Kimi K2.5 measured |
| Finance Agent (Vals AI) | 35.8% | Not measured | Only Kimi K2.5 measured |
| Legal Research Bench (Vals AI) | 15.9% | Not measured | Only Kimi K2.5 measured |
| Excel Modeling Benchmark (Vals AI) | 28.5% | Not measured | Only Kimi K2.5 measured |
| τ²-Bench Telecom | 95.9% | Not measured | Only Kimi K2.5 measured |
| OSWorld | 63.3% | Not measured | Only Kimi K2.5 measured |
| Vending-Bench 2 | $1,198 | Not measured | Only Kimi K2.5 measured |
| Neither model has a result on the other 28 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index32
| Benchmark | Kimi K2.5 | Hy3 | Leader |
|---|---|---|---|
| GPQA Diamond | 84.1% | Not measured | Only Kimi K2.5 measured |
| MMMU Pro (Vals AI) | 84.3% | Not measured | Only Kimi K2.5 measured |
| GPQA Diamond (Artificial Analysis run) | 87.9% | 89.7% | Hy3 |
| Humanity's Last Exam (Artificial Analysis run) | 30.7% | 33.5% | Hy3 |
| ARC-AGI | 65.3% | Not measured | Only Kimi K2.5 measured |
| ARC-AGI-2 | 11.8% | Not measured | Only Kimi K2.5 measured |
| SimpleBench | 46.8% | Not measured | Only Kimi K2.5 measured |
| LMArena Text: hard prompts | 1453 | 1447 | Kimi K2.5 |
| LMArena Text: expert | 1466 | 1461 | Kimi K2.5 |
| LMArena Text: hard prompts in English | 1460 | 1455 | Kimi K2.5 |
| LMArena Vision: diagrams | 1282 | Not measured | Only Kimi K2.5 measured |
| LMArena Vision: homework | 1297 | Not measured | Only Kimi K2.5 measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Kimi K2.5 | Hy3 | Leader |
|---|---|---|---|
| AIME | 95.6% | Not measured | Only Kimi K2.5 measured |
| LMArena Text: math | 1470 | 1473 | Hy3 |
| LMArena Text: mathematical work | 1473 | 1482 | Hy3 |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index31
| Benchmark | Kimi K2.5 | Hy3 | Leader |
|---|---|---|---|
| MMLU Pro | 85.9% | Not measured | Only Kimi K2.5 measured |
| CaseLaw (Vals AI) | 58.7% | Not measured | Only Kimi K2.5 measured |
| CorpFin (Vals AI) | 68.3% | Not measured | Only Kimi K2.5 measured |
| TaxEval (Vals AI) | 74.2% | Not measured | Only Kimi K2.5 measured |
| MortgageTax (Vals AI) | 66.5% | Not measured | Only Kimi K2.5 measured |
| MedQA (Vals AI) | 94.4% | Not measured | Only Kimi K2.5 measured |
| MedCode (Vals AI) | 39.3% | Not measured | Only Kimi K2.5 measured |
| SimpleQA Verified | 34.3% | Not measured | Only Kimi K2.5 measured |
| LMArena Text: science | 1459 | 1457 | Kimi K2.5 |
| LMArena Text: medicine and healthcare | 1448 | 1452 | Hy3 |
| LMArena Text: legal and government | 1441 | 1422 | Kimi K2.5 |
| LMArena Text: business and finance | 1427 | 1424 | Kimi K2.5 |
| Neither model has a result on the other 5 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index53
| Benchmark | Kimi K2.5 | Hy3 | Leader |
|---|---|---|---|
| Design Arena: websites | 1249 | 1230 | Kimi K2.5 |
| Design Arena: UI components | 1236 | 1205 | Kimi K2.5 |
| Design Arena: game dev | 1207 | 1208 | Hy3 |
| Design Arena: data viz | 1219 | 1163 | Kimi K2.5 |
| Design Arena: 3D | 1205 | 1233 | Hy3 |
| Design Arena: all code categories | 1236 | 1227 | Kimi K2.5 |
| Design Arena: SVG | 1149 | 1199 | Hy3 |
| Design Arena: ASCII art | 1165 | 1157 | Kimi K2.5 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index135
| Benchmark | Kimi K2.5 | Hy3 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 49.9% | Not measured | Only Kimi K2.5 measured |
| MedScribe (Vals AI) | 76.4% | Not measured | Only Kimi K2.5 measured |
| IFBench | 70.2% | Not measured | Only Kimi K2.5 measured |
| Long context reasoning (AA-LCR) | 78.0% | 79.0% | Hy3 |
| Fiction.LiveBench | 86.1% | Not measured | Only Kimi K2.5 measured |
| CL-bench | 19.3% | Not measured | Only Kimi K2.5 measured |
| CL-bench Life | 13.2% | Not measured | Only Kimi K2.5 measured |
| LMArena Text | 1445 | 1438 | Kimi K2.5 |
| LMArena Text: instruction following | 1431 | 1426 | Kimi K2.5 |
| LMArena Text: creative writing | 1422 | 1403 | Kimi K2.5 |
| LMArena Vision | 1269 | Not measured | Only Kimi K2.5 measured |
| LMArena Text: English | 1453 | 1448 | Kimi K2.5 |
| LMArena Text: non-English | 1433 | 1426 | Kimi K2.5 |
| LMArena Text: Chinese | 1494 | 1485 | Kimi K2.5 |
| LMArena Text: German | 1441 | 1449 | Hy3 |
| LMArena Text: Japanese | 1423 | 1397 | Kimi K2.5 |
| LMArena Text: Korean | 1412 | 1396 | Kimi K2.5 |
| LMArena Text: French | 1454 | 1456 | Hy3 |
| LMArena Text: Spanish | 1450 | 1457 | Hy3 |
| LMArena Text: Russian | 1435 | 1432 | Kimi K2.5 |
| LMArena Text: Polish | 1445 | 1447 | Hy3 |
| LMArena Text: multi-turn | 1444 | 1436 | Kimi K2.5 |
| LMArena Text: longer queries | 1445 | 1442 | Kimi K2.5 |
| LMArena Text: writing and language | 1425 | 1414 | Kimi K2.5 |
| LMArena Text: entertainment and media | 1417 | 1400 | Kimi K2.5 |
| LMArena Vision: English | 1274 | Not measured | Only Kimi K2.5 measured |
| LMArena Vision: Chinese | 1328 | Not measured | Only Kimi K2.5 measured |
| LMArena Vision: reading text | 1276 | Not measured | Only Kimi K2.5 measured |
| LMArena Vision: humor | 1284 | Not measured | Only Kimi K2.5 measured |
| LMArena Vision: captioning | 1257 | Not measured | Only Kimi K2.5 measured |
| LMArena Vision: recognizing things | 1285 | Not measured | Only Kimi K2.5 measured |
| LMArena Vision: creative writing | 1269 | Not measured | Only Kimi K2.5 measured |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Kimi K2.5 | Hy3 | 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
Hy3 costs less
Repository review
50K input + 3K output tokens
Hy3 costs less
Agent loop
200K input + 10K output tokens
Hy3 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 | MoonshotAI Kimi K2.5 | Tencent Hy3 |
|---|---|---|
| Maker | Moonshot AI | Tencent |
| Weights | Open weights | Open weights |
| Released | January 27, 2026 | July 6, 2026 |
| Context window | 262K | 262K |
| Input $/Mtok | $0.50 | $0.132 |
| Output $/Mtok | $2.50 | $0.528 |
| Coding index | 58.5 | 43.9 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | $0.24 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Kimi K2.5 better than Hy3 for coding?
Pick Kimi K2.5 for coding: it scores 58.5 on the Vibe Coding Index against 43.9 for Hy3. Pick Hy3 when output tokens cost 4.7x less, or when what matters is LMArena WebDev or ALE-Bench, where it leads.
Which is cheaper, Kimi K2.5 or Hy3?
Kimi K2.5 costs $0.50 per million input tokens and $2.50 per million output tokens; Hy3 costs $0.132 and $0.528. Cost per solved task is known for Kimi K2.5 only.
Which has the bigger context window, Kimi K2.5 or Hy3?
Neither: both take 262K tokens.
How many benchmarks is the Kimi K2.5 vs Hy3 comparison based on?
43 benchmarks have a result for both models as of October 21, 2026. Kimi K2.5's coding index rests on 2 independent benchmarks and Hy3's on 1. Where only one model has a result, the page says so instead of naming a winner.