Enter opens the highlighted result. Esc closes.

Claude Fable 5 vs Hy4 flash

Claude Fable 5 leads Hy4 flash on coding, 75.9 to 44.5 on the Vibe Coding Index, and Hy4 flash costs 355.9x less per output token ($0.1405 vs $50.00 per million). Updated November 22, 2026; 10 benchmarks have a result for both.

Claude Fable 5Anthropic
Coding
75.9
Overall
82.1
Output $/M
$50.00
10
Hy4 flashTencent
Coding
44.5
Overall
No data
Output $/M
$0.1405
0
vs boards won of 10 shared

Claude Fable 5 or Hy4 flash: which to pick

Pick Claude Fable 5 for coding: it scores 75.9 on the Vibe Coding Index against 44.5 for Hy4 flash.

Pick Hy4 flash for output tokens 355.9x cheaper ($0.1405 vs $50.00 per million) and a larger context window (1.05M against 1M tokens).

Shared results
10
Claude Fable 5 only
122
Hy4 flash only
2
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
Claude Fable 5 75.9 from 5 benchmarks, Hy4 flash 44.5 from 2 benchmarks.
Widest category
Coding, 25.0 points apart on average over 3 shared benchmarks.
Widest single gap
Terminal-Bench 4 (Vals AI): Claude Fable 5 41.4% against Hy4 flash 15.2%, 35.0 points apart on a 0 to 100 scale.
Output price
Claude Fable 5 $50.00 against Hy4 flash $0.1405 per million output tokens, 355.9x apart.
Context window
Claude Fable 5 takes 1M 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
CategoryClaude Fable 5BarsHy4 flashTies
Coding30
Agentic work20
Web design50
All shared boards100
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for Claude Fable 5 and Hy4 flash
BenchmarkClaude Fable 5Hy4 flashLeader
LMArena WebDev1626Not measuredOnly Claude Fable 5 measured
LiveCodeBench (Vals AI)89.8%Not measuredOnly Claude Fable 5 measured
SWE-bench Verified (Vals AI)95.0%Not measuredOnly Claude Fable 5 measured
Terminal-Bench 4 (Vals AI)41.4%15.2%Claude Fable 5
Vibe Code Bench (Vals AI)90.3%74.8%Claude Fable 5
Code migration (Vals AI)55.1%Not measuredOnly Claude Fable 5 measured
ProgramBench (Vals AI)2.0%Not measuredOnly Claude Fable 5 measured
Terminal-Bench 2.1 (Vals AI)80.5%Not measuredOnly Claude Fable 5 measured
SciCode61.0%Not measuredOnly Claude Fable 5 measured
Terminal-Bench Hard (Artificial Analysis run)62.9%Not measuredOnly Claude Fable 5 measured
Terminal-Bench 4.0 (Artificial Analysis run)42.4%Not measuredOnly Claude Fable 5 measured
FrontierCode53.5%Not measuredOnly Claude Fable 5 measured
FrontierSWE47.0%Not measuredOnly Claude Fable 5 measured
GSO-Bench78.4%Not measuredOnly Claude Fable 5 measured
WeirdML91.9%Not measuredOnly Claude Fable 5 measured
MirrorCode70.0%Not measuredOnly Claude Fable 5 measured
ALE-Bench2041.3Not measuredOnly Claude Fable 5 measured
LMArena Text: coding1519Not measuredOnly Claude Fable 5 measured
LMArena Text: software and IT1512Not measuredOnly Claude Fable 5 measured
LMArena WebDev: React1633Not measuredOnly Claude Fable 5 measured
LMArena WebDev: HTML1651Not measuredOnly Claude Fable 5 measured
LMArena WebDev: from an image1620Not measuredOnly Claude Fable 5 measured
SWE Atlas: Codebase QnA39.0%Not measuredOnly Claude Fable 5 measured
SWE Atlas: Refactoring54.8%Not measuredOnly Claude Fable 5 measured
SWE Atlas: Test Writing55.6%Not measuredOnly Claude Fable 5 measured
GameBench 275.150.5Claude Fable 5
Terminal-Bench 2.183.8%Not measuredOnly Claude Fable 5 measured
Terminal-Bench 3.034.1%Not measuredOnly Claude Fable 5 measured
Terminal-Bench 4.044.5%Not measuredOnly Claude Fable 5 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
Intelligence benchmarks for Claude Fable 5 and Hy4 flash
BenchmarkClaude Fable 5Hy4 flashLeader
Epoch Capabilities Index164.2Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for Claude Fable 5 and Hy4 flash
BenchmarkClaude Fable 5Hy4 flashLeader
Design Arena: agents building web apps1230Not measuredOnly Claude Fable 5 measured
Design Arena: agents building full-stack apps1258Not measuredOnly Claude Fable 5 measured
Design Arena: agents building mobile apps1255Not measuredOnly Claude Fable 5 measured
Design Arena: agents building Android apps1275Not measuredOnly Claude Fable 5 measured
Design Arena: agents building Godot games1261Not measuredOnly Claude Fable 5 measured
Design Arena: agents building games1231Not measuredOnly Claude Fable 5 measured
Design Arena: HTML slides1178Not measuredOnly Claude Fable 5 measured
Design Arena: PowerPoint slides1269Not measuredOnly Claude Fable 5 measured
Finance Agent (Vals AI)56.3%Not measuredOnly Claude Fable 5 measured
Tax Agent Bench (Vals AI)38.3%23.3%Claude Fable 5
Legal Research Bench (Vals AI)49.5%38.5%Claude Fable 5
Harvey's Legal Agent Benchmark (Vals AI)Not measured5.4%Only Hy4 flash measured
Excel Modeling Benchmark (Vals AI)73.7%Not measuredOnly Claude Fable 5 measured
Terminal-Bench-Science (Vals AI)15.7%Not measuredOnly Claude Fable 5 measured
τ²-Bench Telecom98.5%Not measuredOnly Claude Fable 5 measured
APEX-Agents63.6%Not measuredOnly Claude Fable 5 measured
Remote Labor Index16.1%Not measuredOnly Claude Fable 5 measured
PostTrainBench37.3%Not measuredOnly Claude Fable 5 measured
Vending-Bench 2$5,680Not measuredOnly Claude Fable 5 measured
LMArena Search1228Not measuredOnly Claude Fable 5 measured
MCP Atlas83.3%Not measuredOnly Claude Fable 5 measured
τ³-Banking39.7%Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 22 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index17 boards, none shared
Reasoning benchmarks for Claude Fable 5 and Hy4 flash
BenchmarkClaude Fable 5Hy4 flashLeader
GPQA Diamond93.2%Not measuredOnly Claude Fable 5 measured
MMMU Pro (Vals AI)89.3%Not measuredOnly Claude Fable 5 measured
GPQA Diamond (Artificial Analysis run)92.6%Not measuredOnly Claude Fable 5 measured
Humanity's Last Exam (Artificial Analysis run)55.5%Not measuredOnly Claude Fable 5 measured
GPQA Diamond (Epoch AI run)85.9%Not measuredOnly Claude Fable 5 measured
ARC-AGI98.5%Not measuredOnly Claude Fable 5 measured
ARC-AGI-289.2%Not measuredOnly Claude Fable 5 measured
SimpleBench81.9%Not measuredOnly Claude Fable 5 measured
Chess puzzles47.0%Not measuredOnly Claude Fable 5 measured
Mystery game puzzles52.0%Not measuredOnly Claude Fable 5 measured
EBR-bench39.5%Not measuredOnly Claude Fable 5 measured
LMArena Text: hard prompts1508Not measuredOnly Claude Fable 5 measured
LMArena Text: expert1535Not measuredOnly Claude Fable 5 measured
LMArena Text: hard prompts in English1510Not measuredOnly Claude Fable 5 measured
LMArena Vision: diagrams1354Not measuredOnly Claude Fable 5 measured
LMArena Vision: homework1361Not measuredOnly Claude Fable 5 measured
Kagi LLM Benchmark91.4%Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 9 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Math benchmarks for Claude Fable 5 and Hy4 flash
BenchmarkClaude Fable 5Hy4 flashLeader
OTIS Mock AIME100.0%Not measuredOnly Claude Fable 5 measured
FrontierMath, tiers 1 to 387.0%Not measuredOnly Claude Fable 5 measured
FrontierMath, tier 490.2%Not measuredOnly Claude Fable 5 measured
ProofBench95.0%Not measuredOnly Claude Fable 5 measured
LMArena Text: math1516Not measuredOnly Claude Fable 5 measured
LMArena Text: mathematical work1516Not measuredOnly Claude Fable 5 measured
MathArena46.4%Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 7 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index14 boards, none shared
Knowledge benchmarks for Claude Fable 5 and Hy4 flash
BenchmarkClaude Fable 5Hy4 flashLeader
MMLU Pro91.5%Not measuredOnly Claude Fable 5 measured
LegalBench (Vals AI)88.6%Not measuredOnly Claude Fable 5 measured
CorpFin (Vals AI)71.8%Not measuredOnly Claude Fable 5 measured
TaxEval (Vals AI)76.9%Not measuredOnly Claude Fable 5 measured
MortgageTax (Vals AI)68.9%Not measuredOnly Claude Fable 5 measured
MedCode (Vals AI)56.1%Not measuredOnly Claude Fable 5 measured
SimpleQA Verified70.7%Not measuredOnly Claude Fable 5 measured
GeoBench89.0%Not measuredOnly Claude Fable 5 measured
LMArena Text: science1506Not measuredOnly Claude Fable 5 measured
LMArena Text: medicine and healthcare1480Not measuredOnly Claude Fable 5 measured
LMArena Text: legal and government1499Not measuredOnly Claude Fable 5 measured
LMArena Text: business and finance1479Not measuredOnly Claude Fable 5 measured
PRBench Finance53.9%Not measuredOnly Claude Fable 5 measured
PRBench Legal53.9%Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index50
Web design benchmarks for Claude Fable 5 and Hy4 flash
BenchmarkClaude Fable 5Hy4 flashLeader
Design Arena: websites12831227Claude Fable 5
Design Arena: UI components13031262Claude Fable 5
Design Arena: game dev13081202Claude Fable 5
Design Arena: data viz1301Not measuredOnly Claude Fable 5 measured
Design Arena: 3D12841209Claude Fable 5
Design Arena: all code categories12931225Claude Fable 5
Design Arena: SVG1287Not measuredOnly Claude Fable 5 measured
Design Arena: ASCII art1312Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 1 board here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index36 boards, none shared
General benchmarks for Claude Fable 5 and Hy4 flash
BenchmarkClaude Fable 5Hy4 flashLeader
Vals IndexNot measured50.8%Only Hy4 flash measured
Public Benefits Bench (Vals AI)70.4%Not measuredOnly Claude Fable 5 measured
MedScribe (Vals AI)88.5%Not measuredOnly Claude Fable 5 measured
Vals Multimodal Index74.2%Not measuredOnly Claude Fable 5 measured
IFBench63.5%Not measuredOnly Claude Fable 5 measured
Long context reasoning (AA-LCR)82.3%Not measuredOnly Claude Fable 5 measured
GDPval-AA1618Not measuredOnly Claude Fable 5 measured
DTBench98.4%Not measuredOnly Claude Fable 5 measured
LMCA61.2%Not measuredOnly Claude Fable 5 measured
Surface Evolver Bench95.0%Not measuredOnly Claude Fable 5 measured
Furniture assembly35.8%Not measuredOnly Claude Fable 5 measured
LMArena Text1492Not measuredOnly Claude Fable 5 measured
LMArena Text: instruction following1503Not measuredOnly Claude Fable 5 measured
LMArena Text: creative writing1494Not measuredOnly Claude Fable 5 measured
LMArena Vision1325Not measuredOnly Claude Fable 5 measured
LMArena Text: English1499Not measuredOnly Claude Fable 5 measured
LMArena Text: non-English1482Not measuredOnly Claude Fable 5 measured
LMArena Text: Chinese1544Not measuredOnly Claude Fable 5 measured
LMArena Text: German1482Not measuredOnly Claude Fable 5 measured
LMArena Text: Japanese1505Not measuredOnly Claude Fable 5 measured
LMArena Text: Korean1482Not measuredOnly Claude Fable 5 measured
LMArena Text: French1510Not measuredOnly Claude Fable 5 measured
LMArena Text: Spanish1488Not measuredOnly Claude Fable 5 measured
LMArena Text: Russian1501Not measuredOnly Claude Fable 5 measured
LMArena Text: Polish1488Not measuredOnly Claude Fable 5 measured
LMArena Text: multi-turn1504Not measuredOnly Claude Fable 5 measured
LMArena Text: longer queries1510Not measuredOnly Claude Fable 5 measured
LMArena Text: writing and language1502Not measuredOnly Claude Fable 5 measured
LMArena Text: entertainment and media1484Not measuredOnly Claude Fable 5 measured
LMArena Vision: English1325Not measuredOnly Claude Fable 5 measured
LMArena Vision: Chinese1377Not measuredOnly Claude Fable 5 measured
LMArena Vision: reading text1336Not measuredOnly Claude Fable 5 measured
LMArena Vision: humor1348Not measuredOnly Claude Fable 5 measured
LMArena Vision: creative writing1342Not measuredOnly Claude Fable 5 measured
LMArena Document1497Not measuredOnly Claude Fable 5 measured
EQ-Bench 41313Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Fable 5 and Hy4 flash
BenchmarkClaude Fable 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

Claude Fable 5$0.035Fits in one request
Hy4 flash$0.0001Fits in one request

Hy4 flash costs less

Repository review

50K input + 3K output tokens

Claude Fable 5$0.650Fits in one request
Hy4 flash$0.0022Fits in one request

Hy4 flash costs less

Agent loop

200K input + 10K output tokens

Claude Fable 5$2.50Fits 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 Claude Fable 5 and Hy4 flash
SpecificationAnthropic Claude Fable 5Tencent Hy4 flash
MakerAnthropicTencent
WeightsNo public weights listedOpen weights
ReleasedJune 9, 2026November 16, 2026
Context window1M1.05M
Input $/Mtok$10.00$0.035
Output $/Mtok$50.00$0.1405
Coding index75.944.5
Independent measurements behind it52
Cost per solved task$2.16Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Fable 5 better than Hy4 flash for coding?

Pick Claude Fable 5 for coding: it scores 75.9 on the Vibe Coding Index against 44.5 for Hy4 flash. Pick Hy4 flash for output tokens 355.9x cheaper ($0.1405 vs $50.00 per million) and a larger context window (1.05M against 1M tokens).

Which is cheaper, Claude Fable 5 or Hy4 flash?

Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; Hy4 flash costs $0.035 and $0.1405. Cost per solved task is known for Claude Fable 5 only.

Which has the bigger context window, Claude Fable 5 or Hy4 flash?

Hy4 flash, with 1.05M tokens against 1M.

How many benchmarks is the Claude Fable 5 vs Hy4 flash comparison based on?

10 benchmarks have a result for both models as of November 22, 2026. Claude Fable 5's coding index rests on 5 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/claude-fable-5-vs-tencent-hy4-flash" title="Claude Fable 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/claude-fable-5-vs-tencent-hy4-flash">LLMBenchmark.ai, Claude Fable 5 vs Hy4 flash</a></p>