Claude Fable 5 vs Claude Opus 5

$8.75 / task
Wins 3 of 9 benchmarks
$2.19 / task
Wins 1 of 9 benchmarks
Different efforts: max · medium · 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 534.3
DeepSWE 1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition
Fable 569.7
Opus 568.9
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool
Fable 5 · high1,624
Opus 5 · max1,689
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math)
Fable 561
Opus 551.5
SWE-bench Pro (v2 full) SWE-bench Pro (v2 full): Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate
Fable 5—
Opus 5 · xhigh99.4
SWE-bench Pro (v2 hard) SWE-bench Pro (v2 hard): Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate
Fable 5—
Opus 5 · xhigh98
Terminal-Bench Science 0.1 Terminal-Bench Science 0.1: Agents complete expert-authored research workflows across five scientific domains in a terminal
Fable 5—
Opus 5 · max28.6
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 5—
MirrorCode MirrorCode: Agents reimplement software projects by observing their behavior
Fable 5 · high63.9
Opus 5—

Specs

SpecFable 5Opus 5
Input, per 1M$10$5
Output, per 1M$50$25
Cost per task?$8.75$2.19
Speed, tok/s6755
Context1M1M
WeightsClosedClosed
ReleasedJun 2026Jul 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 5
Nothing known.
Opus 5 → Fable 5
Nothing known.