VerdictPal
Join

Models / Anthropic

Claude Fable 5.1

Claude Fable · Released 2026-09-01

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.

Long-horizon coding, multistep research, and dense document work when Opus 5 at higher effort still falls short. Prefer sourced ledger rows over vendor Terminal-Bench-Science tables.

#6 of 23 on Vals Index · current snapshot
68 Vals Index · 3 benchmark rows · 2 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite67
Context1M
Input / 1M$10
Output / 1M$50
Knowledge cutoff2026-06-01
Statussolid
Claude

Family profile

Best published score in each covered benchmark family.

67/100 avg
Knowledge
67
Reasoning
66
Agentic
68

3 tested benchmark families

Editor's note
Recorded from the 1 Sep 2026 Anthropic launch post, API overview, and Vals Index snapshot (67.87%). Same underlying model as Mythos 5.1 with different safeguards. AA API snapshot of 1 Sep 2026 does not yet list an Intelligence Index. Editorial depth still needs a desk pass.
Benchmark placements

Where Claude Fable 5.1 places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
AA-OmniscienceKnowledge#1/ 1267Artificial Analysis — AA-Omniscience2026-09-01
Artificial Analysis Intelligence IndexReasoning#1/ 18466Artificial Analysis — Intelligence Index2026-09-01
Vals IndexAgentic#6/ 2268Vals AI — Vals Index2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where Claude Fable 5.1 shows up, it's highlighted.

KnowledgeClaude Fable 5.1 · 67
  1. 1
    GPT 5.5
    91
  2. 2
    Claude Opus 4.8
    91
  3. 3
    Claude Sonnet 4.6
    91
ReasoningClaude Fable 5.1 · 66
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
AgenticClaude Fable 5.1 · 68
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Newest receipts

Benchmark rows added to the public ledger for Claude Fable 5.1 in the last 120 days. Older rows live in the full table below.

3 recent
BenchmarkFamilyScoreSourceDays ago
Vals IndexAgentic67.87%Vals AI — Vals Index2
Artificial Analysis Intelligence IndexReasoning66%Artificial Analysis — Intelligence Index2
AA-OmniscienceKnowledge67%Artificial Analysis — AA-Omniscience2
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Knowledge67
Reasoning66
Agentic68
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Claude Fable 5.1. Scores link to the original source; gaps mean no public row exists yet.

3 sourced rows

3 of 37 catalog benchmarks have a sourced row for Claude Fable 5.1.

Knowledge

Reasoning

Agentic

Changelog
  1. Claude Fable 5.1 GA on the Claude API, Bedrock, Vertex, and Microsoft Foundry. Cache reads cut to $0.25 / 1M tokens.
Sources