Claude Fable 5 Benchmarks, Pricing & Rankings
Anthropic · 2026-06-30 · Closed · Current
Snapshot 2026-10-14 · updated weekly
Claude Fable 5 ranks #6 of 42 on the AMR leaderboard.
Claude Fable 5 benchmark scores
| GPQA Diamond | 91.9% | |
| MMLU-Pro | 88.2% | |
| SWE-Bench Verified | 74.8% | |
| AIME 2025 | 91.7% | |
| LiveCodeBench v6 | 80.4% | |
| Arena Elo | 1455 |
Claude Fable 5 price, speed & context
Input price
$3.50
per 1M tokens
Output price
$18
per 1M tokens
Speed
138
tok/s
Context
400K
tokens
About Claude Fable 5
Claude Fable 5 defined Anthropic’s mid-flagship line in mid-2026 and still outranks most competitors’ best models a full quarter after release.
Models around Claude Fable 5 in the rankings
More Anthropic models
Claude Fable 5 FAQ
Where does Claude Fable 5 rank?
Claude Fable 5 ranks #6 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 93.8. Its strongest dimension is GPQA Diamond at 91.9%.
How much does Claude Fable 5 cost?
Claude Fable 5 costs $3.50 per million input tokens and $18 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $14.38 per million tokens.
What is the Claude Fable 5 context window?
Claude Fable 5 supports a 400K token context window and generates at a median 138 output tokens per second. That context fits roughly 267 standard documents in a single prompt.
Is Claude Fable 5 open source?
No — Claude Fable 5 is a closed model available only through Anthropic’s official API and authorized cloud partners.
What is better than Claude Fable 5?
Claude Sonnet 5.5 ranks one place higher at #5 with an AMR score of 94.7. Claude Fable 5 still wins 0 of the tracked dimensions head-to-head — check the comparison table to see exactly which.