Kimi K2 Thinking vs Hy3 preview
Updated October 21, 2026. 7 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 Thinking for coding: it scores 63.4 on the Vibe Coding Index against 22.4 for Hy3 preview.
Pick Hy3 preview when output tokens cost 4.2x less, or when what matters is Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
- Shared results
- 7
- Kimi K2 Thinking only
- 23
- Hy3 preview only
- 29
- Like-for-like categories
- 5 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 Thinking
Kimi K2 Thinking scores 63.4 against 22.4.
One benchmark behind each score
Intelligence
AA Intelligence Index
Hy3 preview
Hy3 preview leads, 25.3 against 22.0.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Hy3 preview has a AA Agentic Index result, 24.1.
Directional only
Reasoning
GPQA Diamond
No call
Only Kimi K2 Thinking has a GPQA Diamond result, 78.5%.
Directional only
Math
AIME
No call
Only Kimi K2 Thinking has a AIME result, 85.4%.
Directional only
Knowledge
MMLU Pro
No call
Only Kimi K2 Thinking has a MMLU Pro result, 81.1%.
Directional only
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
No call
Both take 262K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy3 preview
Kimi K2 Thinking $0.0019, Hy3 preview $0.0005 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
- Kimi K2 Thinking 63.4 from 1 benchmark, Hy3 preview 22.4 from 1 benchmark.
- Widest category
- General, 6.1 points apart on average over 2 shared benchmarks.
- Widest single gap
- Long context reasoning (AA-LCR): Kimi K2 Thinking 72.0% against Hy3 preview 64.7%, 7.3 points apart on a 0 to 100 scale.
- Output price
- Kimi K2 Thinking $2.50 against Hy3 preview $0.60 per million output tokens, 4.2x 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 Thinking | Bars | Hy3 preview | Ties |
|---|---|---|---|---|
| Coding | 0 | 1 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 0 | 2 | ||
| General | 2 | 0 | ||
| All shared boards | 3 | 4 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index01
| Benchmark | Kimi K2 Thinking | Hy3 preview | Leader |
|---|---|---|---|
| SWE-bench Verified | 63.4% | Not measured | Only Kimi K2 Thinking measured |
| LMArena WebDev | Not measured | 1357 | Only Hy3 preview measured |
| AA Coding Index | Not measured | 58.8 | Only Hy3 preview measured |
| LiveCodeBench (Vals AI) | 63.1% | Not measured | Only Kimi K2 Thinking measured |
| SWE-bench Verified (Vals AI) | 60.2% | Not measured | Only Kimi K2 Thinking measured |
| LiveCodeBench (Artificial Analysis run) | 85.3% | Not measured | Only Kimi K2 Thinking measured |
| Terminal-Bench Hard (Artificial Analysis run) | 31.1% | 34.1% | Hy3 preview |
| Terminal-Bench | 35.7% | Not measured | Only Kimi K2 Thinking measured |
| WeirdML | 42.8% | Not measured | Only Kimi K2 Thinking measured |
| ALE-Bench | 597.5 | Not measured | Only Kimi K2 Thinking measured |
| LMArena Text: coding | Not measured | 1421 | Only Hy3 preview measured |
| LMArena Text: software and IT | Not measured | 1423 | Only Hy3 preview measured |
| LMArena WebDev: React | Not measured | 1349 | Only Hy3 preview measured |
| LMArena WebDev: HTML | Not measured | 1356 | Only Hy3 preview measured |
| Neither model has a result on the other 24 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Kimi K2 Thinking | Hy3 preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.0 | 25.3 | Hy3 preview |
| Epoch Capabilities Index | 145.8 | Not measured | Only Kimi K2 Thinking measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Kimi K2 Thinking | Hy3 preview | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 24.1 | Only Hy3 preview measured |
| τ²-Bench Telecom | 93.0% | 92.7% | Kimi K2 Thinking |
| METR time horizons | 59.2% | Not measured | Only Kimi K2 Thinking measured |
| Neither model has a result on the other 36 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Kimi K2 Thinking | Hy3 preview | Leader |
|---|---|---|---|
| GPQA Diamond | 78.5% | Not measured | Only Kimi K2 Thinking measured |
| GPQA Diamond (Artificial Analysis run) | 83.8% | 86.7% | Hy3 preview |
| Humanity's Last Exam (Artificial Analysis run) | 23.8% | 27.8% | Hy3 preview |
| LMArena Text: hard prompts | Not measured | 1413 | Only Hy3 preview measured |
| LMArena Text: expert | Not measured | 1422 | Only Hy3 preview measured |
| LMArena Text: hard prompts in English | Not measured | 1416 | Only Hy3 preview measured |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Kimi K2 Thinking | Hy3 preview | Leader |
|---|---|---|---|
| AIME | 85.4% | Not measured | Only Kimi K2 Thinking measured |
| MGSM (Vals AI) | 90.2% | Not measured | Only Kimi K2 Thinking measured |
| AA Math Index | 94.7 | Not measured | Only Kimi K2 Thinking measured |
| AIME 2025 (Artificial Analysis run) | 94.7% | Not measured | Only Kimi K2 Thinking measured |
| LMArena Text: math | Not measured | 1424 | Only Hy3 preview measured |
| LMArena Text: mathematical work | Not measured | 1442 | Only Hy3 preview measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | Kimi K2 Thinking | Hy3 preview | Leader |
|---|---|---|---|
| MMLU Pro | 81.1% | Not measured | Only Kimi K2 Thinking measured |
| LegalBench (Vals AI) | 80.2% | Not measured | Only Kimi K2 Thinking measured |
| CaseLaw (Vals AI) | 65.7% | Not measured | Only Kimi K2 Thinking measured |
| CorpFin (Vals AI) | 60.6% | Not measured | Only Kimi K2 Thinking measured |
| TaxEval (Vals AI) | 71.7% | Not measured | Only Kimi K2 Thinking measured |
| MedQA (Vals AI) | 92.6% | Not measured | Only Kimi K2 Thinking measured |
| MMLU Pro (Artificial Analysis run) | 84.8% | Not measured | Only Kimi K2 Thinking measured |
| LMArena Text: science | Not measured | 1416 | Only Hy3 preview measured |
| LMArena Text: medicine and healthcare | Not measured | 1405 | Only Hy3 preview measured |
| LMArena Text: legal and government | Not measured | 1430 | Only Hy3 preview measured |
| LMArena Text: business and finance | Not measured | 1397 | Only Hy3 preview measured |
| Neither model has a result on the other 6 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Kimi K2 Thinking | Hy3 preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1113 | Not measured | 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 index20
| Benchmark | Kimi K2 Thinking | Hy3 preview | Leader |
|---|---|---|---|
| IFBench | 68.1% | 63.1% | Kimi K2 Thinking |
| Long context reasoning (AA-LCR) | 72.0% | 64.7% | Kimi K2 Thinking |
| CL-bench | 17.6% | Not measured | Only Kimi K2 Thinking measured |
| LMArena Text | Not measured | 1401 | Only Hy3 preview measured |
| LMArena Text: instruction following | Not measured | 1383 | Only Hy3 preview measured |
| LMArena Text: creative writing | Not measured | 1339 | Only Hy3 preview measured |
| LMArena Text: English | Not measured | 1409 | Only Hy3 preview measured |
| LMArena Text: non-English | Not measured | 1390 | Only Hy3 preview measured |
| LMArena Text: Chinese | Not measured | 1435 | Only Hy3 preview measured |
| LMArena Text: French | Not measured | 1425 | Only Hy3 preview measured |
| LMArena Text: Spanish | Not measured | 1399 | Only Hy3 preview measured |
| LMArena Text: Russian | Not measured | 1399 | Only Hy3 preview measured |
| LMArena Text: multi-turn | Not measured | 1411 | Only Hy3 preview measured |
| LMArena Text: longer queries | Not measured | 1402 | Only Hy3 preview measured |
| LMArena Text: writing and language | Not measured | 1370 | Only Hy3 preview measured |
| LMArena Text: entertainment and media | Not measured | 1352 | Only Hy3 preview measured |
| Neither model has a result on the other 30 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Kimi K2 Thinking | Hy3 preview | 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 preview costs less
Repository review
50K input + 3K output tokens
Hy3 preview costs less
Agent loop
200K input + 10K output tokens
Hy3 preview 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 Thinking | Tencent Hy3 preview |
|---|---|---|
| Maker | Moonshot AI | Tencent |
| Weights | Open weights | Open weights |
| Released | November 6, 2025 | April 22, 2026 |
| Context window | 262K | 262K |
| Input $/Mtok | $0.60 | $0.18 |
| Output $/Mtok | $2.50 | $0.60 |
| Coding index | 63.4 | 22.4 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | $0.61 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Kimi K2 Thinking better than Hy3 preview for coding?
Pick Kimi K2 Thinking for coding: it scores 63.4 on the Vibe Coding Index against 22.4 for Hy3 preview. Pick Hy3 preview when output tokens cost 4.2x less, or when what matters is Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
Which is cheaper, Kimi K2 Thinking or Hy3 preview?
Kimi K2 Thinking costs $0.60 per million input tokens and $2.50 per million output tokens; Hy3 preview costs $0.18 and $0.60. Cost per solved task is known for Kimi K2 Thinking only.
Which has the bigger context window, Kimi K2 Thinking or Hy3 preview?
Neither: both take 262K tokens.
How many benchmarks is the Kimi K2 Thinking vs Hy3 preview comparison based on?
7 benchmarks have a result for both models as of October 21, 2026. Kimi K2 Thinking's coding index rests on 1 independent benchmark and Hy3 preview's on 1. Where only one model has a result, the page says so instead of naming a winner.