Claude Fable 5.1 made me a really nice animated pelican
Today is Claude Fable (and Mythos) 5.1 day . Anthropic say that Fable 5.1 "sets a new standard for coding, knowledge work, and long-running problem-solving tasks". Their announcement spends a notable amount of time on scientific research, boasting of a 52.6% score on the brand new Terminal-Bench-Science 0.1 benchmark (first announced on August 27th ),…
Opening of the original on Simon Willison
Summary
Anthropic released Claude Fable 5.1, a new model claiming improved performance in coding, knowledge work, and problem-solving. The model achieved a 52.6% score on the new Terminal-Bench-Science 0.1 benchmark, significantly outperforming competitors like GPT-5.6 Sol. The author tested Fable 5.1's ability to generate animated pelicans across its five reasoning levels, noting that benchmark comparisons are most insightful within model families and across different reasoning efforts.
Why it matters
Why it matters: Anthropic's Fable 5.1 shows a substantial leap in scientific reasoning benchmarks, a key area for AI development. This release challenges competitors like OpenAI and Google Gemini by setting a new bar for specialized tasks. The author's focus on the 'pelican benchmark' and reasoning levels highlights the ongoing effort to evaluate AI capabilities beyond standard metrics. Future attention should be on how this scientific prowess translates to real-world applications and how other labs respond to this benchmark performance.
Related: OpenAI: Claude Fable 5.1 made me a really nice animated pelican · Anthropic: Meet Claude Fable 5.1 · Microsoft: Meet MAI-Transcribe-2: A faster and more accurate speech recognition model · Meta: Trump Administration Sides With OpenAI in New York Times Copyright Lawsuit · xAI: Sam Altman "AGI by December"
Rated high: a launch, deal or policy change that changes what you can do or what it costs.
- GPT‑6 AstraSimon Willison · Web · Sep 3, 2026
- GPT‑6 AstraSimon Willison · Web · Sep 3, 2026
- Claude Fable AI Is Much Stranger Than The Headlines SuggestTwo Minute Papers · Web · Sep 3, 2026
- Fable 5.1 just smoked ASTRA...Wes Roth · Web · Sep 1, 2026
- Fable 5.1 just smoked ASTRA...Wes Roth · Web · Sep 1, 2026
- Runway's Solaris previews the no-code internetThe Rundown AI · Web · Sep 1, 2026
- Mapping global methane emissions from space with deep learningGoogle Research Blog
- Introducing agentic video understanding with GeminiGoogle DeepMind Blog
- Koray Kavukcuoglu on frontier models, coding agents, and building AGIGoogle for Developers on YouTube
- Pairing Google Antigravity with Gemini 3.7 Flash solves notable multi-agent math and engineering problems.The Keyword: Developers
- ReDeck: Step-Level Render-Grounded Refinement for Document-to-Slide GenerationarXiv cs.AI
- LWiAI Podcast #255 - Gemini 3.7, Jalapeño, Qwen 3.8, DronesLast Week in AI
Koray Kavukcuoglu on frontier models, coding agents, and building AGI
Questions people ask
- What is new in Claude Fable 5.1?
- Anthropic claims Fable 5.1 improves coding, knowledge work, and long-running problem-solving. It also achieved a high score on the new Terminal-Bench-Science 0.1 benchmark.
- How does Fable 5.1 perform on science benchmarks?
- Fable 5.1 scored 52.6% on the Terminal-Bench-Science 0.1 benchmark, significantly higher than previous versions and competitors like GPT-5.6 Sol.
More from Simon Willison 2 more
Page generated Sep 3, 2026. Summaries are Subvolts' own; the story belongs to Simon Willison.