Enter opens the highlighted result. Esc closes.

Hy4 flash vs MiMo-V2.5-Pro

Hy4 flash leads MiMo-V2.5-Pro on coding, 44.5 to 31.5 on the Vibe Coding Index, and Hy4 flash costs 12.8x less per output token ($0.1405 vs $1.80 per million). Updated November 22, 2026; 10 benchmarks have a result for both.

Hy4 flashTencent
Coding
44.5
Overall
No data
Output $/M
$0.1405
6
MiMo-V2.5-ProXiaomi
Coding
31.5
Overall
No data
Output $/M
$1.80
4
vs boards won of 10 shared

Hy4 flash or MiMo-V2.5-Pro: which to pick

Pick Hy4 flash for coding: it scores 44.5 on the Vibe Coding Index against 31.5 for MiMo-V2.5-Pro, though on 2 benchmarks against 4.

Pick MiMo-V2.5-Pro for work measured by Design Arena: websites or Design Arena: game dev, where it leads.

Shared results
10
Hy4 flash only
2
MiMo-V2.5-Pro only
61
Like-for-like categories
3 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.

At a glance

Coding index
Hy4 flash 44.5 from 2 benchmarks, MiMo-V2.5-Pro 31.5 from 4 benchmarks.
Widest category
Coding, 24.4 points apart on average over 3 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Hy4 flash 74.8% against MiMo-V2.5-Pro 34.1%, 40.7 points apart on a 0 to 100 scale.
Output price
Hy4 flash $0.1405 against MiMo-V2.5-Pro $1.80 per million output tokens, 12.8x apart.
Context window
Hy4 flash takes 1.05M tokens, MiMo-V2.5-Pro 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.

Boards won, where both have a result
CategoryHy4 flashBarsMiMo-V2.5-ProTies
Coding30
Agentic work20
Web design14
All shared boards64
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for Hy4 flash and MiMo-V2.5-Pro
BenchmarkHy4 flashMiMo-V2.5-ProLeader
LMArena WebDevNot measured1479Only MiMo-V2.5-Pro measured
LiveCodeBench (Vals AI)Not measured81.3%Only MiMo-V2.5-Pro measured
SWE-bench Verified (Vals AI)Not measured74.0%Only MiMo-V2.5-Pro measured
Terminal-Bench 4 (Vals AI)15.2%0.5%Hy4 flash
Vibe Code Bench (Vals AI)74.8%34.1%Hy4 flash
Code migration (Vals AI)Not measured21.6%Only MiMo-V2.5-Pro measured
Terminal-Bench 2.1 (Vals AI)Not measured57.3%Only MiMo-V2.5-Pro measured
SciCodeNot measured50.6%Only MiMo-V2.5-Pro measured
Terminal-Bench Hard (Artificial Analysis run)Not measured43.2%Only MiMo-V2.5-Pro measured
Terminal-Bench 4.0 (Artificial Analysis run)Not measured0.0%Only MiMo-V2.5-Pro measured
ALE-BenchNot measured899.8Only MiMo-V2.5-Pro measured
LMArena Text: codingNot measured1500Only MiMo-V2.5-Pro measured
LMArena Text: software and ITNot measured1494Only MiMo-V2.5-Pro measured
LMArena WebDev: ReactNot measured1468Only MiMo-V2.5-Pro measured
LMArena WebDev: HTMLNot measured1470Only MiMo-V2.5-Pro measured
GameBench 250.537.5Hy4 flash
Neither model has a result on the other 36 boards here
IntelligenceNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Intelligence benchmarks for Hy4 flash and MiMo-V2.5-Pro
BenchmarkHy4 flashMiMo-V2.5-ProLeader
Neither model has a result on 2 boards here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for Hy4 flash and MiMo-V2.5-Pro
BenchmarkHy4 flashMiMo-V2.5-ProLeader
Finance Agent (Vals AI)Not measured41.5%Only MiMo-V2.5-Pro measured
Tax Agent Bench (Vals AI)23.3%11.5%Hy4 flash
Legal Research Bench (Vals AI)38.5%15.9%Hy4 flash
Harvey's Legal Agent Benchmark (Vals AI)5.4%Not measuredOnly Hy4 flash measured
Excel Modeling Benchmark (Vals AI)Not measured55.2%Only MiMo-V2.5-Pro measured
τ²-Bench TelecomNot measured94.2%Only MiMo-V2.5-Pro measured
Neither model has a result on the other 38 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Reasoning benchmarks for Hy4 flash and MiMo-V2.5-Pro
BenchmarkHy4 flashMiMo-V2.5-ProLeader
GPQA DiamondNot measured82.6%Only MiMo-V2.5-Pro measured
GPQA Diamond (Artificial Analysis run)Not measured86.6%Only MiMo-V2.5-Pro measured
Humanity's Last Exam (Artificial Analysis run)Not measured35.7%Only MiMo-V2.5-Pro measured
LMArena Text: hard promptsNot measured1485Only MiMo-V2.5-Pro measured
LMArena Text: expertNot measured1501Only MiMo-V2.5-Pro measured
LMArena Text: hard prompts in EnglishNot measured1494Only MiMo-V2.5-Pro measured
Neither model has a result on the other 20 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Math benchmarks for Hy4 flash and MiMo-V2.5-Pro
BenchmarkHy4 flashMiMo-V2.5-ProLeader
ProofBenchNot measured22.0%Only MiMo-V2.5-Pro measured
LMArena Text: mathNot measured1480Only MiMo-V2.5-Pro measured
LMArena Text: mathematical workNot measured1492Only MiMo-V2.5-Pro measured
Neither model has a result on the other 11 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Knowledge benchmarks for Hy4 flash and MiMo-V2.5-Pro
BenchmarkHy4 flashMiMo-V2.5-ProLeader
MMLU ProNot measured84.6%Only MiMo-V2.5-Pro measured
LegalBench (Vals AI)Not measured77.1%Only MiMo-V2.5-Pro measured
CorpFin (Vals AI)Not measured61.4%Only MiMo-V2.5-Pro measured
TaxEval (Vals AI)Not measured73.8%Only MiMo-V2.5-Pro measured
MedCode (Vals AI)Not measured32.5%Only MiMo-V2.5-Pro measured
LMArena Text: scienceNot measured1482Only MiMo-V2.5-Pro measured
LMArena Text: medicine and healthcareNot measured1472Only MiMo-V2.5-Pro measured
LMArena Text: legal and governmentNot measured1475Only MiMo-V2.5-Pro measured
LMArena Text: business and financeNot measured1467Only MiMo-V2.5-Pro measured
Neither model has a result on the other 12 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index14
Web design benchmarks for Hy4 flash and MiMo-V2.5-Pro
BenchmarkHy4 flashMiMo-V2.5-ProLeader
Design Arena: websites12271258MiMo-V2.5-Pro
Design Arena: UI components12621239Hy4 flash
Design Arena: game dev12021250MiMo-V2.5-Pro
Design Arena: data vizNot measured1255Only MiMo-V2.5-Pro measured
Design Arena: 3D12091221MiMo-V2.5-Pro
Design Arena: all code categories12251255MiMo-V2.5-Pro
Design Arena: SVGNot measured1180Only MiMo-V2.5-Pro measured
Design Arena: ASCII artNot measured1144Only MiMo-V2.5-Pro measured
Neither model has a result on the other 1 board here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index25 boards, none shared
General benchmarks for Hy4 flash and MiMo-V2.5-Pro
BenchmarkHy4 flashMiMo-V2.5-ProLeader
Vals Index50.8%Not measuredOnly Hy4 flash measured
MedScribe (Vals AI)Not measured83.7%Only MiMo-V2.5-Pro measured
IFBenchNot measured79.9%Only MiMo-V2.5-Pro measured
Long context reasoning (AA-LCR)Not measured79.7%Only MiMo-V2.5-Pro measured
GDPval-AANot measured1128Only MiMo-V2.5-Pro measured
DTBenchNot measured84.5%Only MiMo-V2.5-Pro measured
LMCANot measured29.5%Only MiMo-V2.5-Pro measured
LMArena TextNot measured1464Only MiMo-V2.5-Pro measured
LMArena Text: instruction followingNot measured1476Only MiMo-V2.5-Pro measured
LMArena Text: creative writingNot measured1437Only MiMo-V2.5-Pro measured
LMArena Text: EnglishNot measured1477Only MiMo-V2.5-Pro measured
LMArena Text: non-EnglishNot measured1448Only MiMo-V2.5-Pro measured
LMArena Text: ChineseNot measured1507Only MiMo-V2.5-Pro measured
LMArena Text: GermanNot measured1457Only MiMo-V2.5-Pro measured
LMArena Text: JapaneseNot measured1410Only MiMo-V2.5-Pro measured
LMArena Text: KoreanNot measured1439Only MiMo-V2.5-Pro measured
LMArena Text: FrenchNot measured1488Only MiMo-V2.5-Pro measured
LMArena Text: SpanishNot measured1470Only MiMo-V2.5-Pro measured
LMArena Text: RussianNot measured1450Only MiMo-V2.5-Pro measured
LMArena Text: PolishNot measured1461Only MiMo-V2.5-Pro measured
LMArena Text: multi-turnNot measured1475Only MiMo-V2.5-Pro measured
LMArena Text: longer queriesNot measured1481Only MiMo-V2.5-Pro measured
LMArena Text: writing and languageNot measured1451Only MiMo-V2.5-Pro measured
LMArena Text: entertainment and mediaNot measured1437Only MiMo-V2.5-Pro measured
EQ-Bench 4Not measured1198Only MiMo-V2.5-Pro measured
Neither model has a result on the other 24 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Hy4 flash and MiMo-V2.5-Pro
BenchmarkHy4 flashMiMo-V2.5-ProLeader
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

Hy4 flash$0.0001Fits in one request
MiMo-V2.5-Pro$0.0014Fits in one request

Hy4 flash costs less

Repository review

50K input + 3K output tokens

Hy4 flash$0.0022Fits in one request
MiMo-V2.5-Pro$0.029Fits in one request

Hy4 flash costs less

Agent loop

200K input + 10K output tokens

Hy4 flash$0.0084Fits in one request
MiMo-V2.5-Pro$0.114Fits in one request

Hy4 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.

Specifications of Hy4 flash and MiMo-V2.5-Pro
SpecificationTencent Hy4 flashXiaomi MiMo-V2.5-Pro
MakerTencentXiaomi
WeightsOpen weightsOpen weights
ReleasedNovember 16, 2026April 22, 2026
Context window1.05M262K
Input $/Mtok$0.035$0.48
Output $/Mtok$0.1405$1.80
Coding index44.531.5
Independent measurements behind it24
Cost per solved taskNot computable$0.03
SourceOpenRouter listingOpenRouter listing

Questions

Is Hy4 flash better than MiMo-V2.5-Pro for coding?

Pick Hy4 flash for coding: it scores 44.5 on the Vibe Coding Index against 31.5 for MiMo-V2.5-Pro, though on 2 benchmarks against 4. Pick MiMo-V2.5-Pro for work measured by Design Arena: websites or Design Arena: game dev, where it leads.

Which is cheaper, Hy4 flash or MiMo-V2.5-Pro?

Hy4 flash costs $0.035 per million input tokens and $0.1405 per million output tokens; MiMo-V2.5-Pro costs $0.48 and $1.80. Cost per solved task is known for MiMo-V2.5-Pro only.

Which has the bigger context window, Hy4 flash or MiMo-V2.5-Pro?

Hy4 flash, with 1.05M tokens against 262K.

How many benchmarks is the Hy4 flash vs MiMo-V2.5-Pro comparison based on?

10 benchmarks have a result for both models as of November 22, 2026. Hy4 flash's coding index rests on 2 independent benchmarks and MiMo-V2.5-Pro's on 4. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/tencent-hy4-flash-vs-xiaomi-mimo-v2-5-pro" title="Hy4 flash vs MiMo-V2.5-Pro, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/tencent-hy4-flash-vs-xiaomi-mimo-v2-5-pro">LLMBenchmark.ai, Hy4 flash vs MiMo-V2.5-Pro</a></p>