Claude Fable 5.1
Anthropic · Lanzado sept 2026
Anthropic's new frontier flagship is the most capable model publicly available, and it largely fixes the safeguard over-triggering that made Fable 5 frustrating for routine coding. The verdict stays conditional on cost: independent measurement shows more spend per task than Fable 5 despite the cheaper cache reads, because the model thinks longer. Reach for it on demanding reasoning and long-horizon agentic work. For everyday coding, Claude Opus 5 at half the rate remains the better default.
¿Es adecuada para ti?
Bueno para
- Demanding reasoning and long-horizon agentic work — Anthropic's own guidance is to escalate here when Opus 5 at higher effort still falls short
- Agentic scientific research: 52.6% on Terminal-Bench-Science 0.1 against Opus 5's 29.0% and Fable 5's 24.7%
- Context-heavy agent loops — cache reads dropped 75% to $0.25 per 1M, which Anthropic puts at up to ~45% cheaper on highly agentic workloads
- Long-document and whole-repo work: 1M-token context with 128K max output
- Security-adjacent coding that Fable 5 refused — cyber safeguards now permit vulnerability discovery, cutting Claude Code interventions ~60% per session
No recomendado para
- Cost-sensitive everyday coding — Claude Opus 5 is 3 index points behind at $5/$25, half the rate
- Latency-sensitive paths — adaptive thinking is always on and Anthropic rates its comparative latency as the slowest in the lineup
- Budgeting by rate card alone — Artificial Analysis measures ~20% higher cost per task than Fable 5 despite the cache-read cut, because effort drives token count
- Fact-recall work where a confident wrong answer is expensive — at max effort it attempts 93.4% of AA-Omniscience questions, trading more hallucinations for its higher accuracy at no net Omniscience gain
Rendimiento por tarea
Agentic coding
55.8% Terminal-Bench 4.0 and 73.4% CursorBench 3.2.0, with far fewer safeguard interruptions than Fable 5
Scientific research agents
52.6% Terminal-Bench-Science 0.1, roughly double Fable 5 and well ahead of Opus 5's 29.0%
Frontier reasoning
Tops the AA Intelligence Index at 66; 65.0% on Humanity's Last Exam with tools
Long-context work
1M-token window, 128K output, and cache reads at $0.25 per 1M make repeated large-context passes affordable
Computer use
41.7% OSWorld 2.0 strict — competent but not the reason to pay this rate
High-volume cheap inference
Wrong tier entirely; Haiku 4.5 at $1/$5 or Sonnet 5 at $2/$10 own this
Precios
Entrada
$10 / 1M tokens
Salida
$50 / 1M tokens
Contexto
1M context, 128K output; cache $0.25/1M
Pruebas de rendimiento
| Prueba | Puntuación | Fuente |
|---|---|---|
| Artificial Analysis Intelligence Index | 66 | Fuente |
| Terminal-Bench-Science 0.1 | 52.6% | Fuente |
| Terminal-Bench 4.0 | 55.8% | Fuente |
| CursorBench 3.2.0 | 73.4% | Fuente |
| Humanity's Last Exam (no tools) | 60.9% | Fuente |
| Humanity's Last Exam (with tools) | 65.0% | Fuente |
| AutomationBench | 31.4% | Fuente |
| OSWorld 2.0 (strict) | 41.7% | Fuente |
| GDPval-AA v2 | 1853 | Fuente |
| AA-Omniscience accuracy (max effort) | 67.2% | Fuente |
Aún no hay cambios de veredicto
El reloj corre desde el primer día: los cambios aparecerán aquí a medida que evolucione nuestro veredicto.
Fuentes
- Anthropic — Claude models overviewsept 2026
- AiCybr — Fable 5.1 / Mythos 5.1 pricing, benchmarks, accesssept 2026
- Anthropic — Claude Fable 5.1 and Claude Mythos 5.1sept 2026
- Artificial Analysis — Claude Fable 5.1 tops the Intelligence Indexsept 2026
- MarkTechPost — Anthropic releases Claude Fable 5.1 and Mythos 5.1sept 2026
Registro de verificación
Aún no hay comprobaciones de verificación
Todavía no hemos registrado ninguna comprobación de verificación para esta entrada. Cuando se ejecute una, su historial aparecerá aquí.