Anthropic has released Claude Fable 5.1, a model update that sets a new standard for coding, knowledge work, and long-running problem-solving tasks. The release highlights significant performance gains on the new Terminal-Bench-Science 0.1 benchmark, where Fable 5.1 achieved a score of 52.6%, compared to 24.7% for Fable 5, 29.0% for Opus 5, and 22.4% for GPT-5.6 Sol.
- Claude Fable 5.1 introduces five reasoning levels: low, medium, high, xhigh, and max, with no option to disable reasoning entirely.
- Testing on a pelican SVG generation prompt showed that low and medium effort levels skipped reasoning traces entirely, while higher levels produced detailed internal monologues.
- The 'max' reasoning level required 65,927 output tokens and cost $3.30 for the task, resulting in the most detailed visual output among the tested models.
- Animating the generated SVG using the 'high' thinking level cost $1.37 and produced a video with rotating wheels, though the direction was incorrect.
The update allows users to compare model performance across different reasoning effort levels, revealing how increased computational investment impacts output quality and detail.