VerdictPal
Join

Models / Anthropic

Claude Fable 5

Claude Fable · Released 2026-06-09

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%).

Long-horizon agentic work — multi-day coding migrations, finance analysis, vision-heavy rebuilds, and research pipelines that outlast Sonnet or Opus sessions.

#10 of 24 on Vals Index · current snapshot
66 Vals Index · 16 benchmark rows · 4 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite63
Context1M
Input / 1M$10
Output / 1M$50
Knowledge cutoff2026-04-01
Output speed58 t/s
TTFT (default API)54.75s
Statusflagship
ClaudeFactory

Family profile

Best published score in each covered benchmark family.

81/100 avg
Knowledge
65
Reasoning
93
Coding
70
Agentic
100
Long context
77

5 tested benchmark families

Editor's note
Fable 5 is the model we reach for when a task needs days of autonomous work, not minutes. The safety classifiers are conservative — cyber, biology, and chemistry prompts may fall back to Opus 4.8 — so read the system card before pinning it on sensitive workflows. Fable 5.1 is the current Vals Index leader; this page stays the June GA checkpoint.
Benchmark placements

Where Claude Fable 5 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
GDPvalAgentic#1/ 6100Artificial Analysis — GDPval-AA v22026-06-17
Humanity's Last ExamReasoning#1/ 18056Artificial Analysis2026-09-01
SciCodeCoding#1/ 18060Artificial Analysis2026-09-01
AA-OmniscienceKnowledge#2/ 1265Artificial Analysis — AA-Omniscience2026-09-01
Artificial Analysis Intelligence IndexReasoning#2/ 18762Artificial Analysis2026-09-01
DeepSWECoding#3/ 870DeepSWE leaderboard2026-08-04
Terminal-Bench-ScienceAgentic#3/ 921Terminal-Bench-Science 0.1 announcement2026-08-27
AA time to first tokenPerformance#6/ 186Artificial Analysis2026-09-01
CritPtReasoning#6/ 1229Artificial Analysis — CritPt2026-09-01
Vals IndexAgentic#10/ 2366Vals AI — Vals Index2026-09-01
Terminal-BenchAgentic#11/ 18485Artificial Analysis2026-09-01
GPQA DiamondReasoning#17/ 18593Artificial Analysis2026-09-01
τ³-Bench BankingAgentic#22/ 10638Artificial Analysis2026-09-01
AA-LCRLong context#31/ 17977Artificial Analysis2026-09-01
AA output speedPerformance#59/ 187Artificial Analysis2026-09-01
IFBenchReasoning#74/ 12763Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where Claude Fable 5 shows up, it's highlighted.

KnowledgeClaude Fable 5 · 65
  1. 1
    GPT 5.5
    91
  2. 2
    Claude Opus 4.8
    91
  3. 3
    Claude Sonnet 4.6
    91
ReasoningClaude Fable 5 · 93
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
CodingClaude Fable 5 · 70
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticClaude Fable 5 · 100
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextClaude Fable 5 · 77
  1. 1
    Muse Spark 1.2
    83
  2. 2
    Kimi K3
    83
  3. 3
    Gemini 3.5 Flash
    81
Newest receipts

Benchmark rows added to the public ledger for Claude Fable 5 in the last 120 days. Older rows live in the full table below.

16 recent
BenchmarkFamilyScoreSourceDays ago
Vals IndexAgentic66.04%Vals AI — Vals Index5
CritPtReasoning28.6%Artificial Analysis — CritPt5
AA-OmniscienceKnowledge65%Artificial Analysis — AA-Omniscience5
AA-LCRLong context76.67%Artificial Analysis5
AA output speedPerformance58 t/sArtificial Analysis5
AA time to first tokenPerformance54.75sArtificial Analysis5
Artificial Analysis Intelligence IndexReasoning62.1%Artificial Analysis5
GPQA DiamondReasoning92.6%Artificial Analysis5
Humanity's Last ExamReasoning55.5%Artificial Analysis5
IFBenchReasoning63.47%Artificial Analysis5
SciCodeCoding60.2%Artificial Analysis5
τ³-Bench BankingAgentic38.14%Artificial Analysis5
Terminal-BenchAgentic84.64%Artificial Analysis5
Terminal-Bench-ScienceAgentic21.4%Terminal-Bench-Science 0.1 announcement10
DeepSWECoding70%DeepSWE leaderboard33
GDPvalAgentic1818Artificial Analysis — GDPval-AA v281
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.

Knowledge65
Reasoning93
Coding70
Agentic100
Long context77
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Claude Fable 5. Scores link to the original source; gaps mean no public row exists yet.

16 sourced rows

16 of 37 catalog benchmarks have a sourced row for Claude Fable 5.

Knowledge

Reasoning

Coding

Agentic

Long context

Performance

Changelog
  1. Released Claude Fable 5 — first GA Mythos-class model.
  2. Vals Index 66.04% on the 1 Sep snapshot; Fable 5.1 takes the lead at 67.87%.
Sources