Claude Fable 5 vs Claude Opus 4.6

$8.75 / task
Wins 3 of 8 benchmarks
Wins 0 of 8 benchmarks
Different efforts: max · high · Compare all at high
Terminal-Bench 4.0 Terminal-Bench 4.0 · source setting 2: Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite
Fable 542.4
Opus 4.6—
DeepSWE 1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition
Fable 569.7
Opus 4.6 · max31.9
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool
Fable 5 · high1,624
Opus 4.61,547
Terminal-Bench Hard (version unstated) Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal
Fable 562.9
Opus 4.648.5
SWE-bench Pro (private) SWE-bench Pro (private): Agents resolve long-horizon professional repository tasks; public and private splits are separate
Fable 5—
Opus 4.647.1
DeepSWE 1 DeepSWE 1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition
Fable 5—
Opus 4.6 · max27.6
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math)
Fable 561
Opus 4.6—
MirrorCode MirrorCode: Agents reimplement software projects by observing their behavior
Fable 5 · high63.9
Opus 4.6—

Specs

SpecFable 5Opus 4.6
Input, per 1M$10$5
Output, per 1M$50$25
Cost per task?$8.75—
Speed, tok/s6745
Context1M1M
WeightsClosedClosed
ReleasedJun 2026Feb 2026
See images✓✓
Read PDFsPartialPartial
Hear audio——
Watch video——
Call tools✓✓
Force a tool callPartialPartial
Return strict JSON✓✓
Search the web??
Run code??
Use a computer??

What breaks when you switch

Fable 5 → Opus 4.6
Nothing known.
Opus 4.6 → Fable 5
Nothing known.