/tech

The New Stack says it couldn't tell Claude Fable 5.1 and Fable 5 apart on real work · Digg

The New Stack says it couldn't tell Claude Fable 5.1 and Fable 5 apart on real work

The New Stack reports that both models scored perfectly on four real jobs, but Fable 5.1 cost more than twice as much as Fable 5 on the hardest task.

The New Stack reports that Anthropic shipped Claude Fable 5.1 on September 1, claiming doubled performance in agentic research. The publication says it compared Fable 5.1 with Fable 5 on four real jobs and tracked every token. Both scored perfectly, but Fable 5.1's bill was more than double Fable 5's on the hardest task.

Combined views

2.8K

2 posts, first seen 4d ago

1 likes

The New Stack says it couldn't tell Claude Fable 5.1 and Fable 5 apart on real work

The New Stack reports that both models scored perfectly on four real jobs, but Fable 5.1 cost more than twice as much as Fable 5 on the hardest task.

The New Stack reports that Anthropic shipped Claude Fable 5.1 on September 1, claiming doubled performance in agentic research. The publication says it compared Fable 5.1 with Fable 5 on four real jobs and tracked every token. Both scored perfectly, but Fable 5.1's bill was more than double Fable 5's on the hardest task.

Posts from X

2 posts

TN
The New Stack@thenewstack 4 days ago
Claude Fable 5.1 vs. Fable 5: On real work, I couldn't tell them apart.
thenewstack.io
Claude Fable 5.1 vs. Fable 5: On real work, I couldn't tell them apart.
Anthropic shipped Claude Fable 5.1 on September 1, claiming doubled performance in agentic research. I ran it against Fable 5 on four real jobs and tracked every token. Both scored perfectly, and on the hardest task, the new model billed more than double that of the old one.
- likes: 0
- replies: 0
- bookmarks: 0
- reposts: 0
TN
The New Stack@thenewstack 4 days ago
Claude Fable 5.1 vs. Fable 5: On real work, I couldn't tell them apart.
thenewstack.io
Claude Fable 5.1 vs. Fable 5: On real work, I couldn't tell them apart.
Anthropic shipped Claude Fable 5.1 on September 1, claiming doubled performance in agentic research. I ran it against Fable 5 on four real jobs and tracked every token. Both scored perfectly, and on the hardest task, the new model billed more than double that of the old one.
- likes: 1
- replies: 0
- bookmarks: 0
- reposts: 0

Combined views

2.8K

2 posts, first seen 4d ago

1 likes

Posts from X

2 posts

TN
The New Stack@thenewstack 4 days ago
Claude Fable 5.1 vs. Fable 5: On real work, I couldn't tell them apart.
thenewstack.io
Claude Fable 5.1 vs. Fable 5: On real work, I couldn't tell them apart.
Anthropic shipped Claude Fable 5.1 on September 1, claiming doubled performance in agentic research. I ran it against Fable 5 on four real jobs and tracked every token. Both scored perfectly, and on the hardest task, the new model billed more than double that of the old one.
- likes: 0
- replies: 0
- bookmarks: 0
- reposts: 0
TN
The New Stack@thenewstack 4 days ago
Claude Fable 5.1 vs. Fable 5: On real work, I couldn't tell them apart.
thenewstack.io
Claude Fable 5.1 vs. Fable 5: On real work, I couldn't tell them apart.
Anthropic shipped Claude Fable 5.1 on September 1, claiming doubled performance in agentic research. I ran it against Fable 5 on four real jobs and tracked every token. Both scored perfectly, and on the hardest task, the new model billed more than double that of the old one.
- likes: 1
- replies: 0
- bookmarks: 0
- reposts: 0