Hy4 preview vs MiMo-V2.6-Flash
Updated October 21, 2026. 23 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Hy4 preview and MiMo-V2.6-Flash are level for coding, 61.6 against 61.9 on the Vibe Coding Index, so price and context decide.
Pick Hy4 preview when what matters is Code migration (Vals AI) or IOI (Vals AI), where it leads. Pick MiMo-V2.6-Flash when output tokens cost 8.9x less, or when the context window is larger, 1.05M against 1.05M tokens.
- Shared results
- 23
- Hy4 preview only
- 1
- MiMo-V2.6-Flash only
- 43
- 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
No call
Level: 61.6 against 61.9, inside 2 points.
One benchmark behind each score
Intelligence
AA Intelligence Index
No call
Only MiMo-V2.6-Flash has a AA Intelligence Index result, 37.9.
Directional only
General
Vals Index
MiMo-V2.6-Flash
MiMo-V2.6-Flash leads, 54.8% against 53.2%.
Same board, both measured
Long documents
Listed context window
MiMo-V2.6-Flash
MiMo-V2.6-Flash takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiMo-V2.6-Flash
Hy4 preview $0.0021, MiMo-V2.6-Flash $0.0003 per turn.
List prices
At a glance
- Coding index
- Hy4 preview 61.6 from 1 benchmark, MiMo-V2.6-Flash 61.9 from 1 benchmark.
- Widest category
- Math, 12.0 points apart on average over 1 shared benchmark.
- Widest single gap
- Terminal-Bench 2.1 (Vals AI): Hy4 preview 55.1% against MiMo-V2.6-Flash 76.4%, 21.3 points apart on a 0 to 100 scale.
- Output price
- Hy4 preview $2.501 against MiMo-V2.6-Flash $0.28 per million output tokens, 8.9x apart.
- Context window
- Hy4 preview takes 1.05M tokens, MiMo-V2.6-Flash 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 | Hy4 preview | Bars | MiMo-V2.6-Flash | Ties |
|---|---|---|---|---|
| Coding | 3 | 7 | ||
| Agentic work | 2 | 5 | 1 tie | |
| Math | 1 | 0 | ||
| Knowledge | 1 | 0 | ||
| General | 1 | 2 | ||
| All shared boards | 8 | 14 | 1 tie |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index37
| Benchmark | Hy4 preview | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| LMArena WebDev | 1631 | 1634 | MiMo-V2.6-Flash |
| Terminal-Bench 4 (Vals AI) | 8.1% | 24.2% | MiMo-V2.6-Flash |
| Vibe Code Bench (Vals AI) | 77.5% | 79.0% | MiMo-V2.6-Flash |
| Code migration (Vals AI) | 47.4% | 40.9% | Hy4 preview |
| ProgramBench (Vals AI) | 0.0% | 0.5% | MiMo-V2.6-Flash |
| IOI (Vals AI) | 59.3% | 47.7% | Hy4 preview |
| Terminal-Bench 2.1 (Vals AI) | 55.1% | 76.4% | MiMo-V2.6-Flash |
| CyberBench (Vals AI) | 65.4% | 75.4% | MiMo-V2.6-Flash |
| SciCode | Not measured | 51.3% | Only MiMo-V2.6-Flash measured |
| ALE-Bench | Not measured | 1244.2 | Only MiMo-V2.6-Flash measured |
| LMArena Text: coding | Not measured | 1499 | Only MiMo-V2.6-Flash measured |
| LMArena Text: software and IT | Not measured | 1497 | Only MiMo-V2.6-Flash measured |
| LMArena WebDev: React | 1653 | 1648 | Hy4 preview |
| LMArena WebDev: HTML | 1620 | 1641 | MiMo-V2.6-Flash |
| LMArena WebDev: from an image | Not measured | 1596 | Only MiMo-V2.6-Flash measured |
| Neither model has a result on the other 23 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Hy4 preview | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 37.9 | Only MiMo-V2.6-Flash measured |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index25
| Benchmark | Hy4 preview | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| SREBench (Vals AI) | 2.3% | 4.2% | MiMo-V2.6-Flash |
| Finance Agent (Vals AI) | 55.1% | 56.3% | MiMo-V2.6-Flash |
| Tax Agent Bench (Vals AI) | 32.6% | 28.5% | Hy4 preview |
| Legal Research Bench (Vals AI) | 45.2% | 38.0% | Hy4 preview |
| Harvey's Legal Agent Benchmark (Vals AI) | 8.8% | 13.3% | MiMo-V2.6-Flash |
| Excel Modeling Benchmark (Vals AI) | 58.1% | 65.5% | MiMo-V2.6-Flash |
| BioMysteryBench (Vals AI) | 69.3% | 69.3% | Tie |
| Terminal-Bench-Science (Vals AI) | 1.4% | 4.3% | MiMo-V2.6-Flash |
| Vals Science Index | Not measured | 31.7% | Only MiMo-V2.6-Flash measured |
| Neither model has a result on the other 30 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | Hy4 preview | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| MysteryMechanism (Vals AI) | Not measured | 21.6% | Only MiMo-V2.6-Flash measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 35.1% | Only MiMo-V2.6-Flash measured |
| LMArena Text: hard prompts | Not measured | 1475 | Only MiMo-V2.6-Flash measured |
| LMArena Text: expert | Not measured | 1496 | Only MiMo-V2.6-Flash measured |
| LMArena Text: hard prompts in English | Not measured | 1493 | Only MiMo-V2.6-Flash measured |
| LMArena Vision: diagrams | Not measured | 1276 | Only MiMo-V2.6-Flash measured |
| LMArena Vision: homework | Not measured | 1283 | Only MiMo-V2.6-Flash measured |
| Neither model has a result on the other 14 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Hy4 preview | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| ProofBench | 75.0% | 63.0% | Hy4 preview |
| LMArena Text: math | Not measured | 1476 | Only MiMo-V2.6-Flash measured |
| LMArena Text: mathematical work | Not measured | 1478 | Only MiMo-V2.6-Flash measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Hy4 preview | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | 83.8% | Not measured | Only Hy4 preview measured |
| MedCode (Vals AI) | 43.3% | 41.1% | Hy4 preview |
| LMArena Text: science | Not measured | 1462 | Only MiMo-V2.6-Flash measured |
| LMArena Text: medicine and healthcare | Not measured | 1439 | Only MiMo-V2.6-Flash measured |
| LMArena Text: legal and government | Not measured | 1441 | Only MiMo-V2.6-Flash measured |
| LMArena Text: business and finance | Not measured | 1454 | Only MiMo-V2.6-Flash measured |
| Neither model has a result on the other 11 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy4 preview | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | Hy4 preview | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| Vals Index | 53.2% | 54.8% | MiMo-V2.6-Flash |
| Public Benefits Bench (Vals AI) | 68.6% | 67.6% | Hy4 preview |
| SAGE (Vals AI) | Not measured | 43.5% | Only MiMo-V2.6-Flash measured |
| MedScribe (Vals AI) | 83.6% | 85.3% | MiMo-V2.6-Flash |
| Long context reasoning (AA-LCR) | Not measured | 74.3% | Only MiMo-V2.6-Flash measured |
| LMArena Text | Not measured | 1453 | Only MiMo-V2.6-Flash measured |
| LMArena Text: instruction following | Not measured | 1452 | Only MiMo-V2.6-Flash measured |
| LMArena Text: creative writing | Not measured | 1403 | Only MiMo-V2.6-Flash measured |
| LMArena Vision | Not measured | 1256 | Only MiMo-V2.6-Flash measured |
| LMArena Text: English | Not measured | 1476 | Only MiMo-V2.6-Flash measured |
| LMArena Text: non-English | Not measured | 1431 | Only MiMo-V2.6-Flash measured |
| LMArena Text: Chinese | Not measured | 1509 | Only MiMo-V2.6-Flash measured |
| LMArena Text: German | Not measured | 1458 | Only MiMo-V2.6-Flash measured |
| LMArena Text: Japanese | Not measured | 1359 | Only MiMo-V2.6-Flash measured |
| LMArena Text: Korean | Not measured | 1425 | Only MiMo-V2.6-Flash measured |
| LMArena Text: French | Not measured | 1480 | Only MiMo-V2.6-Flash measured |
| LMArena Text: Spanish | Not measured | 1453 | Only MiMo-V2.6-Flash measured |
| LMArena Text: Russian | Not measured | 1409 | Only MiMo-V2.6-Flash measured |
| LMArena Text: Polish | Not measured | 1455 | Only MiMo-V2.6-Flash measured |
| LMArena Text: multi-turn | Not measured | 1447 | Only MiMo-V2.6-Flash measured |
| LMArena Text: longer queries | Not measured | 1459 | Only MiMo-V2.6-Flash measured |
| LMArena Text: writing and language | Not measured | 1424 | Only MiMo-V2.6-Flash measured |
| LMArena Text: entertainment and media | Not measured | 1415 | Only MiMo-V2.6-Flash measured |
| LMArena Vision: English | Not measured | 1269 | Only MiMo-V2.6-Flash measured |
| LMArena Vision: reading text | Not measured | 1270 | Only MiMo-V2.6-Flash measured |
| LMArena Vision: creative writing | Not measured | 1231 | Only MiMo-V2.6-Flash measured |
| Neither model has a result on the other 20 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy4 preview | MiMo-V2.6-Flash | 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-V2.6-Flash costs less
Repository review
50K input + 3K output tokens
MiMo-V2.6-Flash costs less
Agent loop
200K input + 10K output tokens
MiMo-V2.6-Flash 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 Hy4 preview | Xiaomi MiMo-V2.6-Flash |
|---|---|---|
| Maker | Tencent | Xiaomi |
| Weights | Open weights | Open weights |
| Released | August 28, 2026 | September 21, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.834 | $0.14 |
| Output $/Mtok | $2.501 | $0.28 |
| Coding index | 61.6 | 61.9 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Hy4 preview better than MiMo-V2.6-Flash for coding?
Hy4 preview and MiMo-V2.6-Flash are level for coding, 61.6 against 61.9 on the Vibe Coding Index, so price and context decide. Pick Hy4 preview when what matters is Code migration (Vals AI) or IOI (Vals AI), where it leads. Pick MiMo-V2.6-Flash when output tokens cost 8.9x less, or when the context window is larger, 1.05M against 1.05M tokens.
Which is cheaper, Hy4 preview or MiMo-V2.6-Flash?
Hy4 preview costs $0.834 per million input tokens and $2.501 per million output tokens; MiMo-V2.6-Flash costs $0.14 and $0.28. Cost per solved task is known for neither of them.
Which has the bigger context window, Hy4 preview or MiMo-V2.6-Flash?
MiMo-V2.6-Flash, with 1.05M tokens against 1.05M.
How many benchmarks is the Hy4 preview vs MiMo-V2.6-Flash comparison based on?
23 benchmarks have a result for both models as of October 21, 2026. Hy4 preview's coding index rests on 1 independent benchmark and MiMo-V2.6-Flash's on 1. Where only one model has a result, the page says so instead of naming a winner.