Claude Fable 5.1 (Hybrid Reasoning) AI Model Benchmark Evaluation

Intelligence Index

94.8/ 100

Calibrated multi-domain composite

Throughput Speed

54tok/sec

Output streaming throughput

Time To First Token

480ms

Initial chunk server latency

LiveBench Contam-Free

84.7%

September 2026 suite score

LiveBench Multi-Domain Evaluation Breakdown

Monthly refreshed contamination-free test sets

Logical Reasoning89.7%

Coding & Repo Repair86.4%

Mathematics (AIME)88.5%

Data Analysis & Tables82.1%

Language & Comprehension80.2%

Instruction Following81.3%

Sourced Benchmark Evaluations (3)

Verified performance across authoritative benchmarks with provenance tracking.

Benchmark	Status	Score	Trust	Date	Source Type	Provenance
ARC-AGI-2	Nearing Saturation	70%	75	2026-09-12	independent	Source ↗
SWE-bench Verified	Saturated	69.5%	25	2026-08-24	independent	Source ↗
IFEval	Deprecated	81.3%	25	2026-08-19	independent	Source ↗

Anthropic Python SDKAPI Ready

import anthropic

client = anthropic.Anthropic()
message = client.messages.create(
    model="claude-fable-5-1",
    max_tokens=2048,
    temperature=0,
    messages=[{"role": "user", "content": "Execute SWE-bench verified repository fix"}]
)
print(message.content[0].text)

Evaluation & Sourcing Notes

Scores listed for Claude Fable 5.1 (Hybrid Reasoning) represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.

All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.