#14Anthropic· released 2026-06-09

Anthropic: Claude Fable 5.

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

View on OpenRouter ↗
Context
1.0M
Input $/1M
$10.00
Output $/1M
$50.00
Modality
text · image · file

Benchmarks

How these are aggregated →
Arena Elo
1578
LMArena — human blind votes
AA Index
67.0
Artificial Analysis composite
LiveBench
80.3
Contamination-resistant
GPQA
86.8%
Grad-level science reasoning
MMLU-Pro
86.2%
Broad knowledge
SWE-bench
75.6%
Real GitHub bugs (Verified)
Terminal-Bench
58.8%
Agentic shell tasks
ARC-AGI
20.4%
Abstract reasoning
Aider Polyglot
81.5%
Multi-language code editing
Speed
47 tok/s
Median output speed

Profile

Anthropic: Claude Fable 5 is Anthropic's entry at position #14 on the current aggregated leaderboard. Its strongest signals are graduate-level science reasoning, real-world software engineering, unattended agentic work, and very long context. Every figure below is aggregated from the public sources listed on the homepage and refreshed on each pipeline run.

The score spread is comparatively complete for this model, but the standing advice still applies: treat gaps of a few points as ties and validate on your own workload before committing.

How this model's position is computed is documented in the methodology; what each benchmark actually measures is in the benchmark guide. See a figure that disagrees with its source? Report it — accepted corrections apply on the next refresh.

Nearby on the leaderboard