Hy3 preview vs MiMo-V2.5
Updated October 21, 2026. 36 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick MiMo-V2.5 for coding: it scores 34.0 on the Vibe Coding Index against 22.4 for Hy3 preview.
Pick Hy3 preview when what matters is AA Coding Index or AA Intelligence Index, where it leads.
- Shared results
- 36
- Hy3 preview only
- 0
- MiMo-V2.5 only
- 44
- 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
MiMo-V2.5
MiMo-V2.5 scores 34.0 against 22.4.
One benchmark behind each score
Intelligence
AA Intelligence Index
Hy3 preview
Hy3 preview leads, 25.3 against 21.8.
Same board, both measured
Agentic work
AA Agentic Index
Hy3 preview
Hy3 preview leads, 24.1 against 15.8.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only MiMo-V2.5 has a GPQA Diamond result, 81.6%.
Directional only
Knowledge
MMLU Pro
No call
Only MiMo-V2.5 has a MMLU Pro result, 82.9%.
Directional only
Web design
Design Arena: websites
No call
Only MiMo-V2.5 has a Design Arena: websites result, 1266.
Directional only
Long documents
Listed context window
MiMo-V2.5
MiMo-V2.5 takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiMo-V2.5
Hy3 preview $0.0005, MiMo-V2.5 $0.0002 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiMo-V2.5 has the number, $0.01.
Directional only
At a glance
- Coding index
- Hy3 preview 22.4 from 1 benchmark, MiMo-V2.5 34.0 from 1 benchmark.
- Widest category
- Coding, 8.7 points apart on average over 7 shared benchmarks.
- Widest single gap
- LMArena WebDev: React: Hy3 preview 1349 against MiMo-V2.5 1425, 12.7 points apart on a 0 to 100 scale.
- Output price
- Hy3 preview $0.60 against MiMo-V2.5 $0.238 per million output tokens, 2.5x apart.
- Context window
- Hy3 preview takes 262K tokens, MiMo-V2.5 1.05M.
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 | Hy3 preview | Bars | MiMo-V2.5 | Ties |
|---|---|---|---|---|
| Coding | 1 | 6 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 2 | 0 | ||
| Reasoning | 2 | 3 | ||
| Math | 0 | 2 | ||
| Knowledge | 1 | 3 | ||
| General | 1 | 14 | ||
| All shared boards | 8 | 28 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index16
| Benchmark | Hy3 preview | MiMo-V2.5 | Leader |
|---|---|---|---|
| LMArena WebDev | 1357 | 1438 | MiMo-V2.5 |
| AA Coding Index | 58.8 | 56.8 | Hy3 preview |
| LiveCodeBench (Vals AI) | Not measured | 81.5% | Only MiMo-V2.5 measured |
| SWE-bench Verified (Vals AI) | Not measured | 71.0% | Only MiMo-V2.5 measured |
| Vibe Code Bench (Vals AI) | Not measured | 42.2% | Only MiMo-V2.5 measured |
| Code migration (Vals AI) | Not measured | 14.2% | Only MiMo-V2.5 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 60.7% | Only MiMo-V2.5 measured |
| SciCode | Not measured | 43.9% | Only MiMo-V2.5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 34.1% | 41.7% | MiMo-V2.5 |
| ALE-Bench | Not measured | 514.0 | Only MiMo-V2.5 measured |
| LMArena Text: coding | 1421 | 1469 | MiMo-V2.5 |
| LMArena Text: software and IT | 1423 | 1463 | MiMo-V2.5 |
| LMArena WebDev: React | 1349 | 1425 | MiMo-V2.5 |
| LMArena WebDev: HTML | 1356 | 1429 | MiMo-V2.5 |
| Neither model has a result on the other 24 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Hy3 preview | MiMo-V2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 25.3 | 21.8 | Hy3 preview |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Hy3 preview | MiMo-V2.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 24.1 | 15.8 | Hy3 preview |
| Finance Agent (Vals AI) | Not measured | 36.7% | Only MiMo-V2.5 measured |
| Tax Agent Bench (Vals AI) | Not measured | 7.8% | Only MiMo-V2.5 measured |
| Legal Research Bench (Vals AI) | Not measured | 9.1% | Only MiMo-V2.5 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 55.1% | Only MiMo-V2.5 measured |
| τ²-Bench Telecom | 92.7% | 90.6% | Hy3 preview |
| Neither model has a result on the other 33 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index23
| Benchmark | Hy3 preview | MiMo-V2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 81.6% | Only MiMo-V2.5 measured |
| MMMU Pro (Vals AI) | Not measured | 80.0% | Only MiMo-V2.5 measured |
| GPQA Diamond (Artificial Analysis run) | 86.7% | 84.9% | Hy3 preview |
| Humanity's Last Exam (Artificial Analysis run) | 27.8% | 27.2% | Hy3 preview |
| LMArena Text: hard prompts | 1413 | 1450 | MiMo-V2.5 |
| LMArena Text: expert | 1422 | 1459 | MiMo-V2.5 |
| LMArena Text: hard prompts in English | 1416 | 1461 | MiMo-V2.5 |
| LMArena Vision: diagrams | Not measured | 1269 | Only MiMo-V2.5 measured |
| LMArena Vision: homework | Not measured | 1262 | Only MiMo-V2.5 measured |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Hy3 preview | MiMo-V2.5 | Leader |
|---|---|---|---|
| ProofBench | Not measured | 16.0% | Only MiMo-V2.5 measured |
| LMArena Text: math | 1424 | 1436 | MiMo-V2.5 |
| LMArena Text: mathematical work | 1442 | 1451 | MiMo-V2.5 |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | Hy3 preview | MiMo-V2.5 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 82.9% | Only MiMo-V2.5 measured |
| LegalBench (Vals AI) | Not measured | 78.9% | Only MiMo-V2.5 measured |
| CorpFin (Vals AI) | Not measured | 59.9% | Only MiMo-V2.5 measured |
| TaxEval (Vals AI) | Not measured | 71.8% | Only MiMo-V2.5 measured |
| MortgageTax (Vals AI) | Not measured | 59.3% | Only MiMo-V2.5 measured |
| MedCode (Vals AI) | Not measured | 31.9% | Only MiMo-V2.5 measured |
| LMArena Text: science | 1416 | 1440 | MiMo-V2.5 |
| LMArena Text: medicine and healthcare | 1405 | 1432 | MiMo-V2.5 |
| LMArena Text: legal and government | 1430 | 1425 | Hy3 preview |
| LMArena Text: business and finance | 1397 | 1432 | MiMo-V2.5 |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Hy3 preview | MiMo-V2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1266 | Only MiMo-V2.5 measured |
| Design Arena: UI components | Not measured | 1257 | Only MiMo-V2.5 measured |
| Design Arena: game dev | Not measured | 1249 | Only MiMo-V2.5 measured |
| Design Arena: data viz | Not measured | 1249 | Only MiMo-V2.5 measured |
| Design Arena: 3D | Not measured | 1216 | Only MiMo-V2.5 measured |
| Design Arena: all code categories | Not measured | 1260 | Only MiMo-V2.5 measured |
| Design Arena: SVG | Not measured | 1178 | Only MiMo-V2.5 measured |
| Design Arena: ASCII art | Not measured | 1141 | Only MiMo-V2.5 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index114
| Benchmark | Hy3 preview | MiMo-V2.5 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 43.3% | Only MiMo-V2.5 measured |
| MedScribe (Vals AI) | Not measured | 72.2% | Only MiMo-V2.5 measured |
| Vals Multimodal Index | Not measured | 52.8% | Only MiMo-V2.5 measured |
| IFBench | 63.1% | 67.1% | MiMo-V2.5 |
| Long context reasoning (AA-LCR) | 64.7% | 73.0% | MiMo-V2.5 |
| LMArena Text | 1401 | 1428 | MiMo-V2.5 |
| LMArena Text: instruction following | 1383 | 1435 | MiMo-V2.5 |
| LMArena Text: creative writing | 1339 | 1393 | MiMo-V2.5 |
| LMArena Vision | Not measured | 1247 | Only MiMo-V2.5 measured |
| LMArena Text: English | 1409 | 1447 | MiMo-V2.5 |
| LMArena Text: non-English | 1390 | 1405 | MiMo-V2.5 |
| LMArena Text: Chinese | 1435 | 1469 | MiMo-V2.5 |
| LMArena Text: German | Not measured | 1421 | Only MiMo-V2.5 measured |
| LMArena Text: Japanese | Not measured | 1306 | Only MiMo-V2.5 measured |
| LMArena Text: Korean | Not measured | 1361 | Only MiMo-V2.5 measured |
| LMArena Text: French | 1425 | 1448 | MiMo-V2.5 |
| LMArena Text: Spanish | 1399 | 1414 | MiMo-V2.5 |
| LMArena Text: Russian | 1399 | 1396 | Hy3 preview |
| LMArena Text: Polish | Not measured | 1413 | Only MiMo-V2.5 measured |
| LMArena Text: multi-turn | 1411 | 1445 | MiMo-V2.5 |
| LMArena Text: longer queries | 1402 | 1445 | MiMo-V2.5 |
| LMArena Text: writing and language | 1370 | 1409 | MiMo-V2.5 |
| LMArena Text: entertainment and media | 1352 | 1399 | MiMo-V2.5 |
| LMArena Vision: English | Not measured | 1259 | Only MiMo-V2.5 measured |
| LMArena Vision: Chinese | Not measured | 1326 | Only MiMo-V2.5 measured |
| LMArena Vision: reading text | Not measured | 1256 | Only MiMo-V2.5 measured |
| LMArena Vision: humor | Not measured | 1226 | Only MiMo-V2.5 measured |
| LMArena Vision: recognizing things | Not measured | 1189 | Only MiMo-V2.5 measured |
| LMArena Vision: creative writing | Not measured | 1230 | Only MiMo-V2.5 measured |
| Neither model has a result on the other 17 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy3 preview | MiMo-V2.5 | 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
MiMo-V2.5 costs less
Repository review
50K input + 3K output tokens
MiMo-V2.5 costs less
Agent loop
200K input + 10K output tokens
MiMo-V2.5 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 | Tencent Hy3 preview | Xiaomi MiMo-V2.5 |
|---|---|---|
| Maker | Tencent | Xiaomi |
| Weights | Open weights | Open weights |
| Released | April 22, 2026 | April 22, 2026 |
| Context window | 262K | 1.05M |
| Input $/Mtok | $0.18 | $0.119 |
| Output $/Mtok | $0.60 | $0.238 |
| Coding index | 22.4 | 34.0 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | $0.01 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Hy3 preview better than MiMo-V2.5 for coding?
Pick MiMo-V2.5 for coding: it scores 34.0 on the Vibe Coding Index against 22.4 for Hy3 preview. Pick Hy3 preview when what matters is AA Coding Index or AA Intelligence Index, where it leads.
Which is cheaper, Hy3 preview or MiMo-V2.5?
Hy3 preview costs $0.18 per million input tokens and $0.60 per million output tokens; MiMo-V2.5 costs $0.119 and $0.238. Cost per solved task is known for MiMo-V2.5 only.
Which has the bigger context window, Hy3 preview or MiMo-V2.5?
MiMo-V2.5, with 1.05M tokens against 262K.
How many benchmarks is the Hy3 preview vs MiMo-V2.5 comparison based on?
36 benchmarks have a result for both models as of October 21, 2026. Hy3 preview's coding index rests on 1 independent benchmark and MiMo-V2.5's on 1. Where only one model has a result, the page says so instead of naming a winner.