VerdictPal · editorial desk · updated 1 Sep 2026VerdictPal

Compare · Two models, head-to-head

Pick two models. See the diff.

Composite scores, benchmark ranks, capability grids, and pricing per million tokens. All sourced from the same data that powers the model atlas.

Tools Models

Claude Fable 5.1 vs Claude Fable 5

Model A

Model B

MODEL A

Claude Fable 5.1

Anthropic · Claude Fable

Composite 67Intel 683 rows2 sources

Anthropic's 1 Sep 2026 Mythos-class refresh of Fable 5. Same $10 / $50 per 1M tokens, cache reads cut to $0.25 per 1M. 1M context, 128K output, always-on adaptive thinking. Vals Index 67.87% on the 1 Sep 2026 snapshot — ahead of Opus 5 and Fable 5. AA Intelligence Index not in the 1 Sep API snapshot yet.

MODEL B

Claude Fable 5

Anthropic · Claude Fable

Composite 63Intel 6616 rows4 sources

Anthropic's June 2026 Mythos-class GA release. 1M context, 128K output, safety classifiers route high-risk queries to Opus 4.8. $10 / $50 per 1M tokens. Vals Index 66.04% on the 1 Sep 2026 snapshot — behind Fable 5.1 (67.87%) and Opus 5 (67.21%).

Claude Fable 5.13stats won

Tied3stats

Claude Fable 51stats won

Spec showdown

Capacity, price, freshness.

Claude Fable 5.1vsClaude Fable 5

Composite scores are within 5 points — 67 for Claude Fable 5.1 vs 63 for Claude Fable 5. The choice comes down to capability profile and price. Claude Fable 5.1 has the higher Vals/AA intelligence score (68 vs 66).

Composite score
Claude Fable 5.167Winner on this rowClaude Fable 563
Intelligence (Vals/AA)
Claude Fable 5.168Winner on this rowClaude Fable 566
Context window
Claude Fable 5.11MClaude Fable 51M
Max output
Claude Fable 5.1128KClaude Fable 5128K
Input price / 1M (lower wins)
Claude Fable 5.1$10Claude Fable 5$10
Output speed (AA default API)
Claude Fable 5.1—Claude Fable 558 t/sWinner on this row
Time to first token (AA default API)
Claude Fable 5.1—Winner on this rowClaude Fable 554.75s

Composite score

Intelligence (Vals/AA)

Context window

Max output

128K

Input price / 1M (lower wins)

$10

Output speed (AA default API)

—

58 t/s

Time to first token (AA default API)

—

54.75s

Capability grid

What each model can do.

Modalities

Claude Fable 5.1Claude Fable 5

Text●●

Image●●

Audio——

Video——

Code●●

Tool use●●

Reasoning●●

Access

Claude Fable 5.1Claude Fable 5

API●●

Consumer app●●

Open weights——

Managed cloud●●

On-device——

Family profile

Top score per benchmark family.

Knowledge

Reasoning

Agentic

100

Benchmark ranks

Every shared benchmark, side by side.

Knowledge

AA-Omniscience#1/12 · #2/12

67%

65%

Reasoning

Artificial Analysis Intelligence Index#1/184 · #4/184

66%

62.1%

Agentic

Vals Index#6/22 · #9/22

67.87%

66.04%

Dossier facts

Dates, sources, fineprint.

Claude Fable 5.1Claude Fable 5

ProviderAnthropicAnthropic

FamilyClaude FableClaude Fable

Release date2026-09-012026-06-09

Knowledge cutoff2026-06-012026-04-01

Context window1M1M

Max output128K128K

Input price /1M$10$10

Output price /1M$50$50

Statussolidflagship

Composite score6763

Intelligence score6866

Intel sourcevalsvals

Benchmark rows316

Source count24

Freshnessfreshfresh

Pricing checked2026-09-012026-06-09

Ecosystem

Which tools wrap each model.

Claude Fable 5.1

claude

Claude Fable 5

Verdict

Which model to actually pick.

Open Claude Fable 5.1's dossier Open Claude Fable 5's dossier