Enter opens the highlighted result. Esc closes.

Claude Fable 5 vs Claude Opus 4.8

Claude Fable 5 leads Claude Opus 4.8 on coding, 79.3 to 65.0 on the Vibe Coding Index, and Claude Opus 4.8 costs 2.0x less per output token ($25.00 vs $50.00 per million). Updated October 22, 2026; 123 benchmarks have a result for both.

Replace Claude Fable 5 Replace Claude Opus 4.8
Claude Fable 5Anthropic
Coding
79.3
Overall
79.0
Output $/M
$50.00
116
Claude Opus 4.8Anthropic
Coding
65.0
Overall
69.8
Output $/M
$25.00
7
vs boards won of 123 shared

Claude Fable 5 or Claude Opus 4.8: which to pick

Pick Claude Fable 5 for coding: it scores 79.3 on the Vibe Coding Index against 65.0 for Claude Opus 4.8.

Pick Claude Opus 4.8 for output tokens 2.0x cheaper ($25.00 vs $50.00 per million) and work measured by LiveBench browser or Vending-Bench 2, where it leads.

Model AClaude Fable 5Anthropic79.3/1006 independent benchmarks$2.16 per solved taskModel BClaude Opus 4.8Anthropic65.0/1006 independent benchmarks$2.17 per solved task
Shared results
123
Claude Fable 5 only
4
Claude Opus 4.8 only
7
Like-for-like categories
8 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 79.3 from 6 benchmarks, Claude Opus 4.8 65.0 from 6 benchmarks.
Widest category
Math, 12.8 points apart on average over 6 shared benchmarks.
Widest single gap
FrontierMath, tier 4: Claude Fable 5 90.2% against Claude Opus 4.8 56.1%, 34.1 points apart on a 0 to 100 scale.
Output price
Claude Fable 5 $50.00 against Claude Opus 4.8 $25.00 per million output tokens, 2.0x apart.
Context window
Both take 1M tokens.

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 5BarsClaude Opus 4.8Ties
Coding190
Intelligence20
Agentic work212
Reasoning162
Math60
Knowledge101
Web design90
General332
All shared boards1167
CodingLike-for-likeSix of these boards feed the Vibe Coding Index190
Coding benchmarks for Claude Fable 5 and Claude Opus 4.8
BenchmarkClaude Fable 5Claude Opus 4.8Leader
LiveBench coding98.3%77.3%Claude Fable 5
LMArena WebDev16241556Claude Fable 5
AA Coding Index76.574.3Claude Fable 5
LiveCodeBench (Vals AI)89.8%87.8%Claude Fable 5
SWE-bench Verified (Vals AI)95.0%88.6%Claude Fable 5
Terminal-Bench 4 (Vals AI)41.4%23.2%Claude Fable 5
Vibe Code Bench (Vals AI)90.3%82.7%Claude Fable 5
Code migration (Vals AI)55.1%47.3%Claude Fable 5
ProgramBench (Vals AI)2.0%1.0%Claude Fable 5
Terminal-Bench 2.1 (Vals AI)80.5%71.9%Claude Fable 5
SkillsBench (Vals AI)Not measured59.2%Only Claude Opus 4.8 measured
SciCode61.0%54.4%Claude Fable 5
Terminal-Bench Hard (Artificial Analysis run)62.9%58.3%Claude Fable 5
FrontierCode53.5%46.5%Claude Fable 5
FrontierSWE47.0%Not measuredOnly Claude Fable 5 measured
GSO-Bench78.4%47.1%Claude Fable 5
WeirdML91.9%82.9%Claude Fable 5
MirrorCode63.9%Not measuredOnly Claude Fable 5 measured
ALE-Bench2041.3Not measuredOnly Claude Fable 5 measured
LMArena Text: coding15181490Claude Fable 5
LMArena Text: software and IT15131488Claude Fable 5
LMArena WebDev: React16311557Claude Fable 5
LMArena WebDev: HTML16511543Claude Fable 5
LMArena WebDev: from an image1623Not measuredOnly Claude Fable 5 measured
SciCodeNot measured12.3%Only Claude Opus 4.8 measured
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Fable 5 and Claude Opus 4.8
BenchmarkClaude Fable 5Claude Opus 4.8Leader
AA Intelligence Index49.641.8Claude Fable 5
Epoch Capabilities Index163.4159.0Claude Fable 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index212
Agentic work benchmarks for Claude Fable 5 and Claude Opus 4.8
BenchmarkClaude Fable 5Claude Opus 4.8Leader
AA Agentic Index50.741.9Claude Fable 5
Design Arena: agents building web apps12611233Claude Fable 5
Design Arena: agents building full-stack apps12801249Claude Fable 5
Design Arena: agents building mobile apps12641222Claude Fable 5
Design Arena: agents building Android apps12841233Claude Fable 5
Design Arena: agents building Godot games12921231Claude Fable 5
Design Arena: agents building games12851239Claude Fable 5
Design Arena: HTML slides12271171Claude Fable 5
Design Arena: PowerPoint slides12701202Claude Fable 5
Design Arena: spreadsheetsNot measured1303Only Claude Opus 4.8 measured
LiveBench research86.9%81.8%Claude Fable 5
LiveBench browser92.0%96.0%Claude Opus 4.8
LiveBench long agentic53.2%48.3%Claude Fable 5
Finance Agent (Vals AI)56.3%53.9%Claude Fable 5
Tax Agent Bench (Vals AI)38.3%30.0%Claude Fable 5
Legal Research Bench (Vals AI)49.5%43.8%Claude Fable 5
Excel Modeling Benchmark (Vals AI)73.7%69.4%Claude Fable 5
Terminal-Bench-Science (Vals AI)15.7%4.3%Claude Fable 5
Time Horizon Index (Vals AI)Not measured11.8%Only Claude Opus 4.8 measured
τ²-Bench Telecom98.5%94.4%Claude Fable 5
APEX-Agents63.6%48.9%Claude Fable 5
Remote Labor Index16.1%8.3%Claude Fable 5
OSWorld 2.0Not measured20.6%Only Claude Opus 4.8 measured
DeepResearch BenchNot measured50.2%Only Claude Opus 4.8 measured
PostTrainBench41.8%33.8%Claude Fable 5
Vending-Bench 2$5,680$5,787Claude Opus 4.8
LMArena Search12291204Claude Fable 5
Neither model has a result on the other 14 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index162
Reasoning benchmarks for Claude Fable 5 and Claude Opus 4.8
BenchmarkClaude Fable 5Claude Opus 4.8Leader
GPQA Diamond93.2%92.4%Claude Fable 5
LiveBench reasoning89.7%89.2%Claude Fable 5
MMMU Pro (Vals AI)89.3%86.6%Claude Fable 5
GPQA Diamond (Artificial Analysis run)92.6%92.0%Claude Fable 5
Humanity's Last Exam (Artificial Analysis run)55.5%48.7%Claude Fable 5
GPQA Diamond (Epoch AI run)85.9%91.0%Claude Opus 4.8
ARC-AGI98.5%92.5%Claude Fable 5
ARC-AGI-289.2%72.1%Claude Fable 5
SimpleBench81.9%64.8%Claude Fable 5
Chess puzzles47.0%52.0%Claude Opus 4.8
Mystery game puzzles52.0%36.0%Claude Fable 5
EBR-bench39.5%28.6%Claude Fable 5
LMArena Text: hard prompts15071482Claude Fable 5
LMArena Text: expert15341503Claude Fable 5
LMArena Text: hard prompts in English15091487Claude Fable 5
LMArena Vision: diagrams13571315Claude Fable 5
LMArena Vision: homework13611337Claude Fable 5
Kagi LLM Benchmark91.4%88.8%Claude Fable 5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Claude Fable 5 and Claude Opus 4.8
BenchmarkClaude Fable 5Claude Opus 4.8Leader
OTIS Mock AIME100.0%98.3%Claude Fable 5
FrontierMath, tiers 1 to 387.0%80.0%Claude Fable 5
FrontierMath, tier 490.2%56.1%Claude Fable 5
ProofBench95.0%69.0%Claude Fable 5
LMArena Text: math15161486Claude Fable 5
LMArena Text: mathematical work15151497Claude Fable 5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index101
Knowledge benchmarks for Claude Fable 5 and Claude Opus 4.8
BenchmarkClaude Fable 5Claude Opus 4.8Leader
MMLU Pro91.5%89.6%Claude Fable 5
LegalBench (Vals AI)88.6%83.6%Claude Fable 5
CorpFin (Vals AI)71.8%66.7%Claude Fable 5
TaxEval (Vals AI)76.9%75.6%Claude Fable 5
MortgageTax (Vals AI)68.9%69.9%Claude Opus 4.8
MedCode (Vals AI)56.1%53.2%Claude Fable 5
SimpleQA Verified70.7%53.0%Claude Fable 5
LMArena Text: science15061477Claude Fable 5
LMArena Text: medicine and healthcare14801464Claude Fable 5
LMArena Text: legal and government14981477Claude Fable 5
LMArena Text: business and finance14801458Claude Fable 5
FACTS Benchmark SuiteNot measured53.5%Only Claude Opus 4.8 measured
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index90
Web design benchmarks for Claude Fable 5 and Claude Opus 4.8
BenchmarkClaude Fable 5Claude Opus 4.8Leader
Design Arena: websites12951258Claude Fable 5
Design Arena: UI components13161255Claude Fable 5
Design Arena: game dev13351264Claude Fable 5
Design Arena: data viz13041240Claude Fable 5
Design Arena: 3D13181222Claude Fable 5
Design Arena: all code categories13101255Claude Fable 5
Design Arena: SVG13021195Claude Fable 5
Design Arena: ASCII art13291277Claude Fable 5
LiveBench design84.7%78.8%Claude Fable 5
GeneralLike-for-likePublic boards, shown as published, kept out of the index332
General benchmarks for Claude Fable 5 and Claude Opus 4.8
BenchmarkClaude Fable 5Claude Opus 4.8Leader
LiveBench data analysis80.5%66.0%Claude Fable 5
Public Benefits Bench (Vals AI)70.4%68.1%Claude Fable 5
SAGE (Vals AI)51.9%54.8%Claude Opus 4.8
MedScribe (Vals AI)88.5%85.8%Claude Fable 5
Vals Multimodal Index74.2%70.9%Claude Fable 5
IFBench63.5%62.2%Claude Fable 5
Long context reasoning (AA-LCR)82.3%77.7%Claude Fable 5
DTBench98.4%94.9%Claude Fable 5
LMCA61.2%57.5%Claude Fable 5
Surface Evolver Bench95.0%87.5%Claude Fable 5
Furniture assembly35.8%42.5%Claude Opus 4.8
LMArena Text14911461Claude Fable 5
LMArena Text: instruction following15021476Claude Fable 5
LMArena Text: creative writing14941454Claude Fable 5
LMArena Vision13251294Claude Fable 5
LMArena Text: English14981468Claude Fable 5
LMArena Text: non-English14821450Claude Fable 5
LMArena Text: Chinese15431506Claude Fable 5
LMArena Text: German14861472Claude Fable 5
LMArena Text: Japanese15041442Claude Fable 5
LMArena Text: Korean14871431Claude Fable 5
LMArena Text: French15051481Claude Fable 5
LMArena Text: Spanish14981465Claude Fable 5
LMArena Text: Russian15031474Claude Fable 5
LMArena Text: Polish14941459Claude Fable 5
LMArena Text: multi-turn15041476Claude Fable 5
LMArena Text: longer queries15101483Claude Fable 5
LMArena Text: writing and language15011461Claude Fable 5
LMArena Text: entertainment and media14821440Claude Fable 5
LMArena Vision: English13231293Claude Fable 5
LMArena Vision: Chinese13731346Claude Fable 5
LMArena Vision: reading text13371303Claude Fable 5
LMArena Vision: humor13411282Claude Fable 5
LMArena Vision: creative writing13381301Claude Fable 5
LMArena Document14961475Claude Fable 5
Neither model has a result on the other 11 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 Claude Opus 4.8
BenchmarkClaude Fable 5Claude Opus 4.8Leader
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
Claude Opus 4.8$0.018Fits in one request

Claude Opus 4.8 costs less

Repository review

50K input + 3K output tokens

Claude Fable 5$0.650Fits in one request
Claude Opus 4.8$0.325Fits in one request

Claude Opus 4.8 costs less

Agent loop

200K input + 10K output tokens

Claude Fable 5$2.50Fits in one request
Claude Opus 4.8$1.25Fits in one request

Claude Opus 4.8 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 Claude Opus 4.8
SpecificationAnthropic Claude Fable 5Anthropic Claude Opus 4.8
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedJune 9, 2026May 27, 2026
Context window1M1M
Input $/Mtok$10.00$5.00
Output $/Mtok$50.00$25.00
Coding index79.365.0
Independent measurements behind it66
Cost per solved task$2.16$2.17
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Fable 5 better than Claude Opus 4.8 for coding?

Pick Claude Fable 5 for coding: it scores 79.3 on the Vibe Coding Index against 65.0 for Claude Opus 4.8. Pick Claude Opus 4.8 for output tokens 2.0x cheaper ($25.00 vs $50.00 per million) and work measured by LiveBench browser or Vending-Bench 2, where it leads.

Which is cheaper, Claude Fable 5 or Claude Opus 4.8?

Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; Claude Opus 4.8 costs $5.00 and $25.00. Per solved SWE-bench Verified task, Claude Fable 5 costs $2.16 and Claude Opus 4.8 $2.17.

Which has the bigger context window, Claude Fable 5 or Claude Opus 4.8?

Neither: both take 1M tokens.

How many benchmarks is the Claude Fable 5 vs Claude Opus 4.8 comparison based on?

123 benchmarks have a result for both models as of October 22, 2026. Claude Fable 5's coding index rests on 6 independent benchmarks and Claude Opus 4.8's on 6. 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-claude-opus-4-8" title="Claude Fable 5 vs Claude Opus 4.8, 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-claude-opus-4-8">LLMBenchmark.ai, Claude Fable 5 vs Claude Opus 4.8</a></p>