AI Benchmark Model

Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)

Benchmark scores, pricing, speed, and model comparisons for Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback).

Key scores

Intelligence64.8Index score
Coding80.7Index score
Speed65.2Tokens/sec
Blended Cost$20.00Per 1M tokens

Claude Fable 5.1 is an artificial intelligence model developed by Anthropic, released on September 1, 2026. This model features adaptive reasoning with high-effort processing and a default fallback configuration. In standardized testing, the model achieved an intelligence index of 64.8 and a coding index of 80.7, while its math index remains unknown. Benchmark performance results include a GPQA score of 0.934, an HLE score of 0.587, a SciCode score of 0.601, and an LCR score of 0.78. Regarding operational performance, the model maintains an output speed of 65.209 tokens per second with a time to first token of 24.21 seconds. Pricing is structured at $10.00 per million input tokens and $50.00 per million output tokens, resulting in a blended rate of $20.00 per million tokens.

Benchmark results

4 tracked benchmark rows for Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback).

GPQA Reasoning
93.4%
LCR Other
78.0%
SciCode Other
60.1%
HLE Other
58.7%

Comments (0)

No comments yet

Be the first to share your thoughts!