Skip to main content
BenchLM
Data

Claude Fable 5 vs Claude Haiku 5.5

Updated November 21, 2026. Rank says Claude Fable 5 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

Claude Fable 5 has the higher public score, 74.8 versus 63.5, and the 90% score intervals do not overlap. 10 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Anthropic logo

Anthropic

74.8/100

Supported · Public rank #16

90% interval 70.8–78.9

Model B
Anthropic logo

Anthropic

63.5/100

Supported · Public rank #38

90% interval 59.5–67.6

API price per 1M tokens

Claude Fable 5: $10 input / $50 output

Claude Haiku 5.5: $0.10 input / $0.50 output

Context window

Claude Fable 5: 1M

Claude Haiku 5.5: 1M

Released

Claude Fable 5: June 9, 2026

Claude Haiku 5.5: October 7, 2026

Shared results
10
Claude Fable 5 only
17
Claude Haiku 5.5 only
17
Like-for-like categories
6 / 8
Supported: Claude Fable 5 and Claude Haiku 5.5How the comparison works

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

  • Coding work

    Code generation, repair, and software-engineering tasks

    Claude Fable 5

    Claude Fable 5 has the higher public coding point estimate, 78 to 67.9, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

    Confidence: limited
  • Agentic work

    Tool use, computer use, and multi-step task completion

    Claude Fable 5

    Claude Fable 5 has the higher public agentic point estimate, 72.1 to 68.3, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

    Confidence: limited
  • Chat turn cost

    1K fresh input + 500 output tokens

    Claude Haiku 5.5

    Claude Haiku 5.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates
Show secondary and unsupported calls
  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    Claude Haiku 5.5

    Claude Haiku 5.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates
  • Repository review cost

    50K fresh input + 3K output tokens

    Claude Haiku 5.5

    Claude Haiku 5.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates
  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

78.0Claude Fable 567.9Claude Haiku 5.5

Like-for-like · BenchAlign v6.0

Claude Fable 5 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v6.0 lane in every category, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Like-for-like
Claude Fable 5
72.1
Supported · #20/182
Claude Haiku 5.5
68.3
Supported · #25/182
Basis
BenchAlign v6.0 lane · 8 vs 9 public rows
Reading
Claude Fable 5 leads · intervals overlap

Coding

Like-for-like
Claude Fable 5
78.0
Supported · #14/180
Claude Haiku 5.5
67.9
Supported · #28/180
Basis
BenchAlign v6.0 lane · 10 vs 7 public rows
Reading
Claude Fable 5 leads · intervals overlap

Reasoning

Like-for-like
Claude Fable 5
71.0
Supported · #20/161
Claude Haiku 5.5
62.6
Supported · #38/161
Basis
BenchAlign v6.0 lane · 2 vs 4 public rows
Reading
Claude Fable 5 leads · intervals overlap

Multimodal

Like-for-like
Claude Fable 5
70.1
Supported · #19/119
Claude Haiku 5.5
63.9
Supported · #39/119
Basis
BenchAlign v6.0 lane · 3 vs 4 public rows
Reading
Claude Fable 5 leads · intervals overlap

Instruction following

Like-for-like
Claude Fable 5
70.8
Supported · #14/143
Claude Haiku 5.5
58.3
Supported · #37/143
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Claude Fable 5 leads · intervals overlap

Math

Like-for-like
Claude Fable 5
72.2
Supported · #14/125
Claude Haiku 5.5
62.1
Supported · #29/125
Basis
BenchAlign v6.0 lane · 2 vs 2 public rows
Reading
Claude Fable 5 leads · intervals overlap

Knowledge

Directional only
Claude Fable 5
77.0
Estimated · #11/158
Claude Haiku 5.5
50.2
Supported · #84/158
Basis
BenchAlign v6.0 lane · 2 vs 1 public rows
Reading
Directional only

Multilingual

Not comparable
Claude Fable 5
Not ranked
Claude Haiku 5.5
56.1
Estimated · #36/88
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Not comparable

Ranks count the models scored in each category’s BenchAlign v6.0 lane, so denominators differ by category. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Claude Fable 5
$0.035
Fits in one request
Claude Haiku 5.5
$0.00035
Fits in one request

Claude Haiku 5.5 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Fable 5
$0.65
Fits in one request
Claude Haiku 5.5
$0.0065
Fits in one request

Claude Haiku 5.5 has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Claude Fable 5
$0.9
Fits in one request
Claude Haiku 5.5
$0.009
Fits in one request

Claude Haiku 5.5 has the lower modeled cost

Costs use the listed standard API rates.

Your workload

Enter a month of tokens to price it at both models’ listed API rates.

Claude Fable 5
$200.00
per month
Claude Haiku 5.5
$2.00
per month

Standard listed rates, no batch or volume discounts.

Cached input falls back to the list input rate only where a cached rate is unpublished

Price against score, among all priced models

Overall score against output price per 1M tokens, one model per family. Pricing as of November 21, 2026.

Claude Fable 5Claude Haiku 5.5

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • 7 models score at least as high as Claude Fable 5 for the same price or less. The nearest is GPT-6 Astra (score 83.6, also $50.00 per 1M output tokens).
  • Claude Haiku 5.5 is on the efficiency frontier: no cheaper model scores at least as high.

Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.

See Claude Fable 5 on the full price vs performance chart

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Claude Fable 5

$1 per 1M cached input tokens

Claude API pricing

Claude Haiku 5.5

$0.01 per 1M cached input tokens

Claude API pricing

Reasoning profile

Claude Fable 5

Reasoning

Claude Haiku 5.5

Reasoning

Weight access

Claude Fable 5

Proprietary

Claude Haiku 5.5

Proprietary

License

Claude Fable 5

Proprietary

Claude Haiku 5.5

Proprietary

Release date

Claude Fable 5

2026-06-09

Claude Haiku 5.5

2026-10-07

If you already use one of these models

Deployment change
Both entries list Anthropic as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
Quality signal
Claude Fable 5 has the higher public score, 74.8 versus 63.5, and the 90% score intervals do not overlap.
Workload cost
Repository review: $0.65 vs $0.0065. Cache-heavy agent loop: $0.9 vs $0.009.
Context tradeoff
Both models list 1M.
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Claude Fable 5 or Claude Haiku 5.5?

Claude Fable 5 has the higher public score, 74.8 versus 63.5, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.

Which is better for coding, Claude Fable 5 or Claude Haiku 5.5?

Claude Fable 5 has the higher public coding point estimate, 78 to 67.9, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which is better for agentic tasks, Claude Fable 5 or Claude Haiku 5.5?

Claude Fable 5 has the higher public agentic tasks point estimate, 72.1 to 68.3, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which costs less, Claude Fable 5 or Claude Haiku 5.5?

For the stated presets, chat costs $0.035 on Claude Fable 5 and $0.00035 on Claude Haiku 5.5; repository review costs $0.65 and $0.0065; the cache-heavy agent loop costs $0.9 and $0.009. Costs use the listed standard API rates.

Which has the larger context window, Claude Fable 5 or Claude Haiku 5.5?

Both models list the same context window, 1M.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence44 rows

Agentic

  • Claude Fable 572.67%
    Claude Haiku 5.558.62%

    Claude Fable 5 leads this result

  • Terminal-Bench 4.1

    Shared source
    Claude Fable 544.90%
    Claude Haiku 5.540.00%

    Claude Fable 5 leads this result

  • Terminal-Bench 3.0

    Claude Fable 534.0%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • Terminal-Bench 2.1

    Claude Fable 584.3%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • OSWorld-Verified

    Claude Fable 585%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Claude Fable 580.5%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • ApprenticeBench

    Claude Fable 534%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • MazeBench

    Claude Fable 511%
    Source
    Claude Haiku 5.51%
    Source

    Claude Fable 5 leads this result

  • Agents' Last Exam (Linux)

    Claude Fable 5—
    Claude Haiku 5.557.0%
    Source

    Not directly comparable

  • Terminal-Bench 4.0

    Claude Fable 5—
    Claude Haiku 5.539.20%
    Source

    Not directly comparable

  • HLE w/ tools

    Claude Fable 5—
    Claude Haiku 5.557.4%
    Source

    Not directly comparable

  • Hermes Index

    Claude Fable 5—
    Claude Haiku 5.537.0%
    Source

    Not directly comparable

  • Hermes Bench

    Claude Fable 5—
    Claude Haiku 5.571.0%
    Source

    Not directly comparable

  • OSWorld 2.1 Offline

    Claude Fable 5—
    Claude Haiku 5.572.4%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Claude Fable 595%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • SWE-bench Pro

    Claude Fable 580%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • FrontierSWE v2

    Shared source
    Claude Fable 547.0%
    Claude Haiku 5.543.8%

    Claude Fable 5 leads this result

  • FrontierCode 1.1 Main

    Claude Fable 553.5%
    Source
    Claude Haiku 5.546.4%
    Source

    Claude Fable 5 leads this result

  • Terminal-Bench 2.1

    Claude Fable 584.3%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • cursorBench31

    Claude Fable 570.6%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • CursorBench 3.2

    Claude Fable 570.5%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • VulcanBench v3

    Claude Fable 589.5%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • LiveCodeBench (Vals)

    Claude Fable 589.8%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • SWE-bench (Vals)

    Claude Fable 595.0%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • Bug Hunt Bench

    Claude Fable 5—
    Claude Haiku 5.521.5 fixes
    Source

    Not directly comparable

  • FrontierCode 2.0

    Claude Fable 5—
    Claude Haiku 5.528.9%
    Source

    Not directly comparable

  • CursorBench 4.0

    Claude Fable 5—
    Claude Haiku 5.548.4%
    Source

    Not directly comparable

  • VulcanBench Frontier v4

    Claude Fable 5—
    Claude Haiku 5.592.2%
    Source

    Not directly comparable

  • CursorBench 4.1

    Claude Fable 5—
    Claude Haiku 5.548.4%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-1

    Claude Fable 598.50%
    Source
    Claude Haiku 5.589.00%
    Source

    Claude Fable 5 leads this result

  • ARC-AGI-2

    Claude Fable 589.2%
    Source
    Claude Haiku 5.561.3%
    Source

    Claude Fable 5 leads this result

  • ARC-AGI-3

    Claude Fable 5—
    Claude Haiku 5.50.5%
    Source

    Not directly comparable

  • ARC-AGI-3 Provider Adapter

    Claude Fable 5—
    Claude Haiku 5.52.82%
    Source

    Not directly comparable

Multimodal

  • ParseBench-1

    Shared source
    Claude Fable 569.79%
    Claude Haiku 5.556.06%

    Claude Fable 5 leads this result

  • Blueprint-Bench 2

    Claude Fable 538.6%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • OfficeQA Pro

    Claude Fable 557.9%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • ParseBench-2

    Claude Fable 5—
    Claude Haiku 5.571.24%
    Source

    Not directly comparable

  • PerceptionBench (tools)

    Claude Fable 5—
    Claude Haiku 5.578.6%
    Source

    Not directly comparable

  • Chartography (no tools)

    Claude Fable 5—
    Claude Haiku 5.546.4%
    Source

    Not directly comparable

Knowledge

  • GPQA Diamond (Vals)

    Claude Fable 593.2%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • MMLU-Pro (Vals)

    Claude Fable 591.5%
    Source
    Claude Haiku 5.5—

    Not directly comparable

  • HLE w/o tools

    Claude Fable 5—
    Claude Haiku 5.545.9%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    Claude Fable 587.018%
    Claude Haiku 5.575.088%

    Claude Fable 5 leads this result

  • FrontierMath v2 (Tier 4)

    Shared source
    Claude Fable 590.200%
    Claude Haiku 5.546.341%

    Claude Fable 5 leads this result

44 public results · 10 shared

Watch Claude Fable 5 vs Claude Haiku 5.5

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 7,000+ subscribers.

Last updated November 21, 2026