SShogo Bench

Claude Opus 4.8 vs Claude Sonnet 5

Claude Opus 4.8 leads Claude Sonnet 5 by 3.9 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 4.8 wins 16 and Claude Sonnet 5 wins 4 of 20 shared benchmarks. Claude Sonnet 5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.8Claude Sonnet 5
Agentic coding6357
Long-horizon autonomy6665
Knowledge-work agents4343
Computer use4740
Security & context learning5551

Shared benchmarks

BenchmarkClaude Opus 4.8Claude Sonnet 5
APEX-Agentsindex48.9%54.5%
DeepSWEindex59.0%53.8%
Vending-Bench 2index$5,787$6,378
GSO-Benchindex47.1%37.3%
Chess Puzzles52.0%45.0%
CritPt20.9%16.9%
DTBench94.9%92.5%
FrontierCode46.5%42.7%
FrontierMath Tier 456.1%29.3%
FrontierMath Tiers 1-380.0%65.6%
GeoBench81.0%74.0%
GPQA Diamond91.0%90.5%
LMCA57.5%50.0%
MirrorCode65.6%63.3%
OTIS Mock AIME98.3%94.7%
ProofBench69.0%77.0%
SciCode53.5%54.3%
SimpleBench64.8%60.6%
SimpleQA Verified53.0%33.7%
WebDev Arena15591537

Specs and price

Claude Opus 4.8Claude Sonnet 5
Agent Index56.3 (#20)52.4 (#32)
Agent $/M$2.31$0.92
Input / output $/M$5.00 / $25.00$2.00 / $10.00
Context1M1M
ReleasedMay 28, 2026Jun 30, 2026
WeightsClosedClosed
API hosts65

Don’t pick one. Route.

Shogo can run Claude Opus 4.8 and Claude Sonnet 5 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo