【文章标题】：Claude Fable 5.1 made me a really nice animated pelican
【文章标题】：Claude寓言5.1为我制作了一只超赞的动画鹈鹕
【文章正文】：
Today is Claude Fable (and Mythos) 5.1 day.
今天是Claude寓言（及神话）5.1发布日。
Anthropic say that Fable 5.1 “sets a new standard for coding, knowledge work, and long-running problem-solving tasks”.
Anthropic宣称Fable 5.1”为编程、知识工作和长期问题解决任务设立了新标准”。
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), up from 24.7% for Fable 5, 29.0% for Opus 5 and 22.4% for GPT-5.6 Sol.
其公告大篇幅强调科研能力，炫耀在全新Terminal-Bench-Science 0.1基准测试（8月27日首次公布）中获得52.6%的分数，较Fable 5的24.7%、Opus 5的29.0%和GPT-5.6 Sol的22.4%有显著提升。
Other benchmarks show slightly improved scores, but none as impressive as the Science one.
其他基准测试分数略有提高，但都不及科学基准的突破性表现。
But how well can it pelican?
但它画鹈鹕的能力如何呢？
Back in July I wrote about how I was losing faith in the pelican benchmark - its connection to how good the models were at other tasks didn’t seem to hold as strongly as it did back in 2025.
早在七月份我就撰文提及对”鹈鹕基准”失去信心——该基准与模型其他任务能力的关联性已不如2025年时显著。
The most interesting insights I get from it now are comparisons within model families, and particularly comparisons for the same prompt at different reasoning effort levels.
如今该测试最有价值的洞察是模型家族内部的横向比较，尤其是同一提示词在不同推理强度下的表现差异。
Fable 5.1 has five reasoning levels: low, medium, high, xhigh, max - and no option to turn off reasoning entirely.
Fable 5.1设有五级推理强度：低、中、高、超高、极限——且无法完全关闭推理功能。
I fixed an issue in llm-anthropic which caused reasoning traces not to be correctly recorded, then ran some prompts.
我修复了llm-anthropic中导致推理痕迹无法正确记录的问题后，运行了几组提示词。
Here’s the full set of pelicans for all of the reasoning levels, each with the full reasoning transcript. I’ll replicate them here:
以下是所有推理级别生成的完整鹈鹕SVG及对应推理过程，现复现如下：
Low and medium, both without reasoning?
低中两档竟无推理痕迹？
Next, a bit of a mystery. This is what I got for effort low:
接下来出现谜团。这是低强度下的产出：
The transcript doesn’t show any summarized reasoning tokens, and the output token count is 1,998. With Claude that output token count includes reasoning tokens. It took 23.8 seconds and cost 10.017 cents.
记录中未见任何推理标记，输出token数1998（Claude的计数包含推理token）。耗时23.8秒，花费0.10017美元。
I bumped that up to medium and got this:
提升至中档后得到：
Weirdly, that one also shows no reasoning text and used 1,977 output tokens - 21 tokens less than low. It took 23 seconds and cost 9.912 cents.
诡异的是仍无推理文本，且输出token减少21个至1977。耗时23秒，花费0.09912美元。
So for this particular prompt (“Generate an SVG of a pelican riding a bicycle”) Fable 5.1 appeared to skip reasoning entirely at both low and medium settings.
可见对于”生成骑自行车鹈鹕的SVG”这个特定提示，Fable 5.1在低中两档似乎完全跳过了推理环节。
High
高强度档：
Here’s high - 29.6 seconds, 2,612 output tokens, 13.087 cents:
高强度下：29.6秒，2612输出token，0.13087美元：
This one did do a bit of reasoning, summary here:
此次出现少量推理，摘要如下：
I’m planning the SVG layout for a pelican riding a bicycle, with a sky and ground background, a bicycle with two spoked wheels, frame, seat and handlebars, and a white-bodied pelican with a long neck and orange beak positioned on top.
”正在规划骑自行车鹈鹕的SVG布局：包含天空地面背景、双轮自行车框架、白色长颈橙喙鹈鹕置于车座”
Really not much difference from low and medium, though.
但与低中档差异仍不明显。
Extra High
超高档：
At xhigh things got radically different. 36,767 output tokens, 7 minutes 51 seconds, $1.83!
超高档发生质变：36767输出token，7分51秒，1.83美元！
The reasoning trace is pretty lengthy, and includes details like this:
推理痕迹相当冗长，包含如下细节：
Adding the eye, wings stretching down to the handlebar grip, orange legs reaching to the pedals, and a small tail feather, while keeping the pelican intentionally oversized compared to the bike for comic effect. […]
”添加眼睛、延伸至车把的翅膀、够到踏板的橙色腿部和小尾羽，并刻意将鹈鹕比例放大以营造喜剧效果”
I’ll accept the slight thickness as charming rather than overengineering it.
”我将接受略显粗笨的线条视作萌点而非过度设计”
Max
极限档：
Setting effort to max gave me the best pelican I’ve seen from any of Anthropic’s models. 65,927 output tokens, 13 minutes and 54 seconds, $3.30:
极限档产出我见过Anthropic模型中最棒的鹈鹕：65927输出token，13分54秒，3.3美元：
There’s a lot to like about this. The background is tasteful, the legs are clearly on either side of the frame, the feet are on the pedals, the wing is on the handlebars, the pelican has a cute blue hat and there’s a basket with a fish.
亮点颇多：雅致背景、双腿分跨车架、双足踩踏板、翅膀扶车把、鹈鹕戴蓝色小帽、车筐还有条鱼。
It’s still not showing nearly the same level of flair as Gemini 3.7 Flash, but I didn’t ask for flair - I asked for an SVG, and that’s what I got.
虽不及Gemini 3.7 Flash那般炫技，但我要求的本就是SVG而非艺术性。
Some highlights from that reasoning trace:
推理痕迹中的精华片段：
Adding pedal shapes near both feet, with the far foot on the second leg partially visible behind the frame. I’m considering whether to add a small scarf or cap for extra character, but leaning toward keeping it simple to avoid clutter.
”在双足处添加踏板形状，后腿足部在车架后若隐若现。考虑添加围巾或帽子增添个性，但倾向保持简洁”
Now I’m debating a bicycle helmet on the head versus the pelican’s signature crest—the beak and pouch already read clearly as “pelican,” so a helmet could reinforce the bicycle theme without losing identity, though it might compete with the crest for visual space.
”纠结该用自行车头盔还是保留鹈鹕冠羽——喙部已足够彰显物种特征，头盔能强化自行车主题又不失辨识度，但可能与冠羽争夺视觉空间”
I realize the beak at (484,84) would overlap with the dome helmet, so I need to shrink the helmet so it only covers the top of the head, adjusting its arc endpoints to sit higher and narrower so the beak can attach cleanly at the front without collision. […]
”意识到喙部(484,84)会与圆顶头盔重叠，需缩小头盔仅覆盖头顶，调整弧线端点使其更高更窄，确保喙部能无碰撞地衔接”
I’m adding a darker tip region to represent the primary feathers, then reconsidering the trailing edge to include scalloped feather curves instead of one smooth line for a more natural look. […]
”添加深色翼尖表现飞羽，将羽缘改为扇贝状曲线替代平滑线条以更自然”
Now I’m checking the vent line placements on the helmet, making sure they sit far enough inside the helmet’s edge given the stroke width and rounded caps, and confirming each vent stays within the helmet’s circular boundary. […]
”校验头盔透气孔位置，根据描边宽度和圆角确保其与边缘保持距离，确认所有气孔都在头盔圆形边界内”
I decide skipping a handlebar bell and tire highlights since they’re unnecessary additions. Now I’m reconsidering the front fork’s curve — the current control point pulls the shape backward when it should bow forward for a proper rake, so I need t
”决定省略车铃和轮胎高光等冗余元素。重新考量前叉曲线——当前控制点使形状后缩，本应前凸形成合理倾斜角”