SShogo Bench

Claude Opus 4.8 vs Claude Sonnet 5.5

Claude Sonnet 5.5 leads Claude Opus 4.8 by 12.7 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 4.8 wins 1 and Claude Sonnet 5.5 wins 18 of 19 shared benchmarks. Claude Sonnet 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.8Claude Sonnet 5.5
Agentic coding6379
Long-horizon autonomy6675
Knowledge-work agents4357
Computer use4761
Security & context learning5561

Shared benchmarks

BenchmarkClaude Opus 4.8Claude Sonnet 5.5
APEX-Agentsindex48.9%75.5%
Vending-Bench 2index$5,787$11,165
ARC-AGI92.5%96.5%
ARC-AGI-272.1%83.9%
Chess Puzzles52.0%59.0%
CritPt20.9%31.4%
DTBench94.9%97.3%
FrontierCode46.5%52.1%
FrontierMath Tier 456.1%80.5%
FrontierMath Tiers 1-380.0%88.8%
GPQA Diamond91.0%95.6%
LMCA57.5%68.3%
MirrorCode65.6%97.8%
OTIS Mock AIME98.3%100.0%
ProofBench69.0%100.0%
SciCode53.5%61.0%
SimpleBench64.8%75.9%
SimpleQA Verified53.0%46.5%
WebDev Arena15591786

Specs and price

Claude Opus 4.8Claude Sonnet 5.5
Agent Index56.3 (#20)69 (#9)
Agent $/M$2.31$0.84
Input / output $/M$5.00 / $25.00$2.00 / $10.00
Context1M1M
ReleasedMay 28, 2026Sep 28, 2026
WeightsClosedClosed
API hosts65

Don’t pick one. Route.

Shogo can run Claude Opus 4.8 and Claude Sonnet 5.5 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo