Claude Opus 4.7 vs Claude Opus 4.8

Wins 1 of 7 benchmarks
$4.08 / task
Wins 3 of 7 benchmarks
Different efforts: high · max · 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
Opus 4.7—
Opus 4.821.7
DeepSWE 1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition
Opus 4.7 · max49.3
Opus 4.859
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool
Opus 4.71,558
Opus 4.8 · high1,556
DeepSWE 1 DeepSWE 1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition
Opus 4.740.3
Opus 4.858.2
Terminal-Bench Hard (version unstated) Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal
Opus 4.754.5
Opus 4.858.3
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math)
Opus 4.7—
Opus 4.854.4
MirrorCode MirrorCode: Agents reimplement software projects by observing their behavior
Opus 4.731.1
Opus 4.8—

Specs

SpecOpus 4.7Opus 4.8
Input, per 1M$5$5
Output, per 1M$25$25
Cost per task?—$4.08
Speed, tok/s5966
Context1M1M
WeightsClosedClosed
ReleasedApr 2026May 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

Opus 4.7 → Opus 4.8
Nothing known.
Opus 4.8 → Opus 4.7
Nothing known.