MMODELYST
Models/Claude Fable 5
MDL

Claude Fable 5

Anthropic

Verified against Artificial Analysis · Jun 15, 2026
Capability
95
percentile index
Price /M
$10 / $50
in / out
Context
1M
tokens
Avg score
71.6
7 benchmarks
AA Intelligence
64.9
index
Speed
77 tok/s
TTFT 1m 35s
Released
Jun 9, 2026
About

Claude Fable 5 is a proprietary model in the Claude family from Anthropic. Benchmarked on 7 evals, averaging 71.6.

Benchmark scores · 7
avg 71.6 — higher is better
τ²-bench
98.5
GPQA Diamond
92.6
AA Long-Context Reasoning
70
IFBench
63.5
Terminal-Bench Hard
62.9
SciCode
60.2
Humanity's Last Exam
53.3
Details
PublisherAnthropic
FamilyClaude
Parameters
License
WeightsClosed
ReleasedJun 9, 2026
Performance & price
Output speed77 tok/s
Latency (TTFT)1m 35s
Price in / out$10 / $50 per 1M
Blended price$20 / 1M
Coding index62.0

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

Capability over time
GPQA Diamondfirst seen at 92.6
6d ago
Humanity's Last Examfirst seen at 53.3
6d ago
SciCodefirst seen at 60.2
6d ago
IFBenchfirst seen at 63.5
6d ago
τ²-benchfirst seen at 98.5
6d ago
Terminal-Bench Hardfirst seen at 62.9
6d ago

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$50/M