Enter opens the highlighted result. Esc closes.

Mistral Medium 3.5 vs Hy4 flash

Hy4 flash leads Mistral Medium 3.5 on coding, 44.5 to 25.4 on the Vibe Coding Index, and Hy4 flash costs 53.4x less per output token ($0.1405 vs $7.50 per million). Updated November 22, 2026; 9 benchmarks have a result for both.

Mistral Medium 3.5Mistral AI
Coding
25.4
Overall
33.2
Output $/M
$7.50
0
Hy4 flashTencent
Coding
44.5
Overall
No data
Output $/M
$0.1405
9
vs boards won of 9 shared

Mistral Medium 3.5 or Hy4 flash: which to pick

Pick Hy4 flash for coding: it scores 44.5 on the Vibe Coding Index against 25.4 for Mistral Medium 3.5, though on 2 benchmarks against 3.

Mistral Medium 3.5 is neither cheaper nor larger in context, and leads no benchmark both models were measured on.

Shared results
9
Mistral Medium 3.5 only
78
Hy4 flash only
3
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
Mistral Medium 3.5 25.4 from 3 benchmarks, Hy4 flash 44.5 from 2 benchmarks.
Widest category
Coding, 47.7 points apart on average over 2 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Mistral Medium 3.5 2.9% against Hy4 flash 74.8%, 72.0 points apart on a 0 to 100 scale.
Output price
Mistral Medium 3.5 $7.50 against Hy4 flash $0.1405 per million output tokens, 53.4x apart.
Context window
Mistral Medium 3.5 takes 262K tokens, Hy4 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.

Boards won, where both have a result
CategoryMistral Medium 3.5BarsHy4 flashTies
Coding02
Agentic work02
Web design05
All shared boards09
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
Coding benchmarks for Mistral Medium 3.5 and Hy4 flash
BenchmarkMistral Medium 3.5Hy4 flashLeader
LMArena WebDev1263Not measuredOnly Mistral Medium 3.5 measured
SWE-bench Verified (Vals AI)66.4%Not measuredOnly Mistral Medium 3.5 measured
Terminal-Bench 4 (Vals AI)Not measured15.2%Only Hy4 flash measured
Vibe Code Bench (Vals AI)2.9%74.8%Hy4 flash
Code migration (Vals AI)5.1%Not measuredOnly Mistral Medium 3.5 measured
Terminal-Bench 2.1 (Vals AI)39.0%Not measuredOnly Mistral Medium 3.5 measured
SciCode40.2%Not measuredOnly Mistral Medium 3.5 measured
Terminal-Bench Hard (Artificial Analysis run)33.3%Not measuredOnly Mistral Medium 3.5 measured
Terminal-Bench 4.0 (Artificial Analysis run)0.0%Not measuredOnly Mistral Medium 3.5 measured
FrontierCode 2.01.8%Not measuredOnly Mistral Medium 3.5 measured
ALE-Bench764.0Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: coding1461Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: software and IT1458Not measuredOnly Mistral Medium 3.5 measured
LMArena WebDev: React1252Not measuredOnly Mistral Medium 3.5 measured
LMArena WebDev: HTML1310Not measuredOnly Mistral Medium 3.5 measured
GameBench 227.050.5Hy4 flash
Neither model has a result on the other 36 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Intelligence benchmarks for Mistral Medium 3.5 and Hy4 flash
BenchmarkMistral Medium 3.5Hy4 flashLeader
AA Intelligence Index4.6Not measuredOnly Mistral Medium 3.5 measured
Epoch Capabilities Index141.6Not measuredOnly Mistral Medium 3.5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for Mistral Medium 3.5 and Hy4 flash
BenchmarkMistral Medium 3.5Hy4 flashLeader
Finance Agent (Vals AI)32.1%Not measuredOnly Mistral Medium 3.5 measured
Tax Agent Bench (Vals AI)4.5%23.3%Hy4 flash
Legal Research Bench (Vals AI)9.1%38.5%Hy4 flash
Harvey's Legal Agent Benchmark (Vals AI)Not measured5.4%Only Hy4 flash measured
Excel Modeling Benchmark (Vals AI)11.2%Not measuredOnly Mistral Medium 3.5 measured
τ²-Bench Telecom94.2%Not measuredOnly Mistral Medium 3.5 measured
Neither model has a result on the other 38 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
Reasoning benchmarks for Mistral Medium 3.5 and Hy4 flash
BenchmarkMistral Medium 3.5Hy4 flashLeader
GPQA Diamond34.9%Not measuredOnly Mistral Medium 3.5 measured
GPQA Diamond (Artificial Analysis run)74.8%Not measuredOnly Mistral Medium 3.5 measured
Humanity's Last Exam (Artificial Analysis run)13.8%Not measuredOnly Mistral Medium 3.5 measured
HLE-Diamond (Artificial Analysis run)4.7%Not measuredOnly Mistral Medium 3.5 measured
CritPt v2, hard subset (Artificial Analysis run)0.5%Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: hard prompts1436Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: expert1432Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: hard prompts in English1445Not measuredOnly Mistral Medium 3.5 measured
LMArena Vision: diagrams1255Not measuredOnly Mistral Medium 3.5 measured
LMArena Vision: homework1229Not measuredOnly Mistral Medium 3.5 measured
Kagi LLM Benchmark41.4%Not measuredOnly Mistral Medium 3.5 measured
Neither model has a result on the other 15 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Math benchmarks for Mistral Medium 3.5 and Hy4 flash
BenchmarkMistral Medium 3.5Hy4 flashLeader
ProofBench9.0%Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: math1432Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: mathematical work1440Not measuredOnly Mistral Medium 3.5 measured
Neither model has a result on the other 11 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
Knowledge benchmarks for Mistral Medium 3.5 and Hy4 flash
BenchmarkMistral Medium 3.5Hy4 flashLeader
MMLU Pro75.3%Not measuredOnly Mistral Medium 3.5 measured
CaseLaw (Vals AI)44.2%Not measuredOnly Mistral Medium 3.5 measured
CorpFin (Vals AI)58.8%Not measuredOnly Mistral Medium 3.5 measured
TaxEval (Vals AI)68.0%Not measuredOnly Mistral Medium 3.5 measured
MortgageTax (Vals AI)28.9%Not measuredOnly Mistral Medium 3.5 measured
MedCode (Vals AI)33.8%Not measuredOnly Mistral Medium 3.5 measured
AA-Omniscience-38.7Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: science1427Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: medicine and healthcare1407Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: legal and government1437Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: business and finance1426Not measuredOnly Mistral Medium 3.5 measured
Neither model has a result on the other 10 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index05
Web design benchmarks for Mistral Medium 3.5 and Hy4 flash
BenchmarkMistral Medium 3.5Hy4 flashLeader
Design Arena: websites11291227Hy4 flash
Design Arena: UI components10621262Hy4 flash
Design Arena: game dev10511202Hy4 flash
Design Arena: data viz1115Not measuredOnly Mistral Medium 3.5 measured
Design Arena: 3D10281209Hy4 flash
Design Arena: all code categories11031225Hy4 flash
Design Arena: SVG934Not measuredOnly Mistral Medium 3.5 measured
Design Arena: ASCII art1048Not measuredOnly Mistral Medium 3.5 measured
Neither model has a result on the other 1 board here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index33 boards, none shared
General benchmarks for Mistral Medium 3.5 and Hy4 flash
BenchmarkMistral Medium 3.5Hy4 flashLeader
Vals IndexNot measured50.8%Only Hy4 flash measured
SAGE (Vals AI)72.0%Not measuredOnly Mistral Medium 3.5 measured
MedScribe (Vals AI)67.7%Not measuredOnly Mistral Medium 3.5 measured
Vals Multimodal Index34.8%Not measuredOnly Mistral Medium 3.5 measured
IFBench68.8%Not measuredOnly Mistral Medium 3.5 measured
Long context reasoning (AA-LCR)69.3%Not measuredOnly Mistral Medium 3.5 measured
GDPval-AA769Not measuredOnly Mistral Medium 3.5 measured
DTBench75.5%Not measuredOnly Mistral Medium 3.5 measured
LMCA26.1%Not measuredOnly Mistral Medium 3.5 measured
Surface Evolver Bench26.9%Not measuredOnly Mistral Medium 3.5 measured
LMArena Text1421Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: instruction following1415Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: creative writing1373Not measuredOnly Mistral Medium 3.5 measured
LMArena Vision1222Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: English1433Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: non-English1405Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: Chinese1444Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: German1460Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: Korean1386Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: French1449Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: Spanish1412Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: Russian1397Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: Polish1429Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: multi-turn1423Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: longer queries1415Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: writing and language1383Not measuredOnly Mistral Medium 3.5 measured
LMArena Text: entertainment and media1382Not measuredOnly Mistral Medium 3.5 measured
LMArena Vision: English1242Not measuredOnly Mistral Medium 3.5 measured
LMArena Vision: Chinese1244Not measuredOnly Mistral Medium 3.5 measured
LMArena Vision: reading text1232Not measuredOnly Mistral Medium 3.5 measured
LMArena Vision: humor1218Not measuredOnly Mistral Medium 3.5 measured
LMArena Vision: creative writing1199Not measuredOnly Mistral Medium 3.5 measured
EQ-Bench 4983Not measuredOnly Mistral Medium 3.5 measured
Neither model has a result on the other 16 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Mistral Medium 3.5 and Hy4 flash
BenchmarkMistral Medium 3.5Hy4 flashLeader
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

Mistral Medium 3.5$0.0053Fits in one request
Hy4 flash$0.0001Fits in one request

Hy4 flash costs less

Repository review

50K input + 3K output tokens

Mistral Medium 3.5$0.098Fits in one request
Hy4 flash$0.0022Fits in one request

Hy4 flash costs less

Agent loop

200K input + 10K output tokens

Mistral Medium 3.5$0.375Fits in one request
Hy4 flash$0.0084Fits 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 Mistral Medium 3.5 and Hy4 flash
SpecificationMistral Medium 3.5Tencent Hy4 flash
MakerMistral AITencent
WeightsOpen weightsOpen weights
ReleasedApril 30, 2026November 16, 2026
Context window262K1.05M
Input $/Mtok$1.50$0.035
Output $/Mtok$7.50$0.1405
Coding index25.444.5
Independent measurements behind it32
Cost per solved task$6.02Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Mistral Medium 3.5 better than Hy4 flash for coding?

Pick Hy4 flash for coding: it scores 44.5 on the Vibe Coding Index against 25.4 for Mistral Medium 3.5, though on 2 benchmarks against 3. Mistral Medium 3.5 is neither cheaper nor larger in context, and leads no benchmark both models were measured on.

Which is cheaper, Mistral Medium 3.5 or Hy4 flash?

Mistral Medium 3.5 costs $1.50 per million input tokens and $7.50 per million output tokens; Hy4 flash costs $0.035 and $0.1405. Cost per solved task is known for Mistral Medium 3.5 only.

Which has the bigger context window, Mistral Medium 3.5 or Hy4 flash?

Hy4 flash, with 1.05M tokens against 262K.

How many benchmarks is the Mistral Medium 3.5 vs Hy4 flash comparison based on?

9 benchmarks have a result for both models as of November 22, 2026. Mistral Medium 3.5's coding index rests on 3 independent benchmarks and Hy4 flash's on 2. 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/mistral-medium-3-5-vs-tencent-hy4-flash" title="Mistral Medium 3.5 vs Hy4 flash, 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/mistral-medium-3-5-vs-tencent-hy4-flash">LLMBenchmark.ai, Mistral Medium 3.5 vs Hy4 flash</a></p>