Willison puts Claude Fable 5.1 through his pelican SVG test
TL;DR
- Simon Willison ran Anthropic's new Claude Fable 5.1 through his SVG pelican-on-a-bicycle prompt at all five reasoning settings, from low to max.
- Max-effort mode consumed 65,927 tokens over 13m 54s at $3.30, with an additional $1.37 to animate the resulting SVG.
- Fable 5.1 scored 52.6% on Terminal-Bench-Science 0.1, ahead of Fable 5 (24.7%), Opus 5 (29.0%) and GPT-5.6 Sol (22.4%).
Simon Willison put Anthropic's newly released Claude Fable 5.1 through his running pelican-on-a-bicycle SVG test on his blog, publishing the results on 1 September 2026. The model exposes five reasoning settings: low, medium, high, xhigh, and max, with no option to turn reasoning off. Running the prompt at max effort consumed 65,927 tokens over 13m 54s at a cost of $3.30, with an additional $1.37 to animate the resulting SVG.
Willison quotes Anthropic's own framing that Fable 5.1 'sets a new standard for coding, knowledge work, and long-running problem-solving tasks,' then leads with his own question: 'But how well can it pelican?' The verdict is favourable but bounded. 'It's still not showing nearly the same level of flair as Gemini 3.7 Flash,' he writes.
On Terminal-Bench-Science 0.1, Willison logs Fable 5.1 at 52.6%, well ahead of Fable 5 at 24.7%, Opus 5 at 29.0%, and GPT-5.6 Sol at 22.4%. Two of the AI writers we track shared the post the same day.
Shared on Bluesky by 2 AI experts
-
Simon Willison @simonwillison.net
A few notes on Anthropic's new Claude Fable 5.1 - with Max thinking level I got the best SVG pelican I've had from any Anthropic model (at a hefty cost of $3.30!), which I then had it animate simonwillison.net/2026/Sep/1…
View on Bluesky →
Originally reported by simonwillison.net
Read the original article →Original headline: Claude Fable 5.1 made me a really nice animated pelican