AA-OmniscienceVerified
65%
AA-Omniscience Accuracy
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.
Long-horizon agentic work — multi-day coding migrations, finance analysis, vision-heavy rebuilds, and research pipelines that outlast Sonnet or Opus sessions.
Composite62
Context1M
Input / 1M$10
Output / 1M$50
Knowledge cutoff2026-04-01
Output speed65 t/s
Statusflagship
Family profile
Best published score in each covered benchmark family.
79/100 avg
- Knowledge
- 65
- Reasoning
- 93
- Coding
- 70
- Agentic
- 85
- Long context
- 82
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.Benchmark placements
Per-benchmark positions
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.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| AA-Omniscience | Knowledge | #2/ 12 | 65 | Artificial Analysis — AA-Omniscience | 2026-09-01 |
| DeepSWE | Coding | #3/ 8 | 70 | DeepSWE leaderboard | 2026-08-04 |
| Humanity's Last Exam | Reasoning | #3/ 186 | 56 | Artificial Analysis | 2026-09-28 |
| SciCode | Coding | #3/ 97 | 61 | Artificial Analysis | 2026-09-28 |
| Terminal-Bench-Science | Agentic | #3/ 9 | 21 | Terminal-Bench-Science 0.1 announcement | 2026-08-27 |
| CritPt | Reasoning | #6/ 12 | 29 | Artificial Analysis — CritPt | 2026-09-01 |
| Terminal-Bench | Agentic | #15/ 167 | 85 | Artificial Analysis | 2026-09-28 |
| AA-LCR | Long context | #18/ 184 | 82 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #21/ 184 | 93 | Artificial Analysis | 2026-09-28 |
| AA output speed | Performance | #96/ 195 | Artificial Analysis | 2026-10-12 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where Claude Fable 5 shows up, it's highlighted.
KnowledgeClaude Fable 5 · 65
- 167
- 265
- 361
ReasoningClaude Fable 5 · 93
- 196
- 295
- 395
Math
- 152
- 252
- 350
CodingClaude Fable 5 · 70
- 174
- 273
- 370
AgenticClaude Fable 5 · 85
- 191
- 289
- 389
Long contextClaude Fable 5 · 82
- 189
- 286
- 385
Newest receipts
10 recentLast 120 days
Benchmark rows added to the public ledger for Claude Fable 5 in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA output speed | Performance | 65 t/s | Artificial Analysis | 10 |
| AA-LCR | Long context | 82.33% | Artificial Analysis | 24 |
| GPQA Diamond | Reasoning | 92.6% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 55.5% | Artificial Analysis | 24 |
| SciCode | Coding | 61% | Artificial Analysis | 24 |
| Terminal-Bench | Agentic | 84.64% | Artificial Analysis | 24 |
| CritPt | Reasoning | 28.6% | Artificial Analysis — CritPt | 51 |
| AA-Omniscience | Knowledge | 65% | Artificial Analysis — AA-Omniscience | 51 |
| Terminal-Bench-Science | Agentic | 21.4% | Terminal-Bench-Science 0.1 announcement | 56 |
| DeepSWE | Coding | 70% | DeepSWE leaderboard | 79 |
Family coverage
Best score per family
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.
Price vs. performance
Where Claude Fable 5 sits on the scatter
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
AnthropicOpenAIGoogleAlibabaMetaZhipuxAIDeepSeekMiniMaxXiaomiMoonshotOtherMeituanMistralNVIDIACohere
Full benchmark ledger
Every catalog benchmark for Claude Fable 5. Scores link to the original source; gaps mean no public row exists yet.
10 of 13 catalog benchmarks have a sourced row for Claude Fable 5.
Knowledge
Reasoning
CritPtVerified
28.6%
CritPt composite (AA run)
GPQA DiamondVerified
92.6%
GPQA Diamond (AA run)
Humanity's Last ExamVerified
55.5%
HLE (AA run)
Coding
Agentic
Terminal-BenchVerified
84.64%
Terminal-Bench v2.1 (AA run)
Terminal-Bench-ScienceVerified
21.4%
TB-Science 0.1 resolution (Claude Code)
Long context
AA-LCRVerified
82.33%
AA-LCR (AA run)
Performance
AA output speedVerified
65 t/s
Median output tokens/s (1k prompt, default provider)
Changelog
Version history
- Released Claude Fable 5 — first GA Mythos-class model.
Sources
Where the numbers come from
- Anthropic announcement· checked 2026-06-09
- Anthropic pricing· checked 2026-06-09
- Vals model page· checked 2026-06-09
Questions this model page answers
Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.
What is Claude Fable 5?
Claude Fable 5 is a Anthropic model: 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.
What is Claude Fable 5 for?
Long-horizon agentic work — multi-day coding migrations, finance analysis, vision-heavy rebuilds, and research pipelines that outlast Sonnet or Opus sessions.
What does Claude Fable 5 cost?
Claude Fable 5 lists $10 input and $50 output per 1M tokens. Pricing last checked 2026-06-09.
How large is the Claude Fable 5 context window?
Claude Fable 5 publishes a 1M token context window.
What is the VerdictPal status of Claude Fable 5?
Claude Fable 5 carries Flagship status on the model atlas.
The Pack · Editorial newsletter
Know when the rules move.
One short email when a university changes its AI rule for theses, or a research tool changes its pricing or privacy terms. No tracking, no third-party analytics. Unsubscribe in one click.