Claude Fable 5.1 made me a nice animated pelican

Anthropic’s Claude Fable 5.1 achieved a 52.6% score on the new Terminal-Bench-Science 0.1 benchmark, far surpassing Fable 5 (24.7%), Opus 5 (29.0%) and GPT-5.6 Sol (22.4%). When prompted to generate an SVG of a pelican riding a bicycle, the model produced progressively richer outputs as reasoning effort increased, ranging from minimal output at low/medium settings to a detailed 65,927-token SVG with elaborate features at the max setting, costing $3.30 and taking nearly 14 minutes.