SShogo Bench

Claude Sonnet 5 vs Claude Sonnet 5.5

Claude Sonnet 5.5 leads Claude Sonnet 5 by 16.6 points on the Shogo Agent Index. Claude Sonnet 5 wins 0 and Claude Sonnet 5.5 wins 18 of 18 shared benchmarks. Claude Sonnet 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5Claude Sonnet 5.5
Agentic coding5779
Long-horizon autonomy6575
Knowledge-work agents4357
Computer use4061
Security & context learning5161

Shared benchmarks

BenchmarkClaude Sonnet 5Claude Sonnet 5.5
APEX-Agentsindex54.5%75.5%
Vending-Bench 2index$6,378$11,165
CursorBenchindex34.1%55.5%
Chess Puzzles45.0%59.0%
CritPt16.9%31.4%
DTBench92.5%97.3%
FrontierCode42.7%52.1%
FrontierMath Tier 429.3%80.5%
FrontierMath Tiers 1-365.6%88.8%
GPQA Diamond90.5%95.6%
LMCA50.0%68.3%
MirrorCode63.3%97.8%
OTIS Mock AIME94.7%100.0%
ProofBench77.0%100.0%
SciCode54.3%61.0%
SimpleBench60.6%75.9%
SimpleQA Verified33.7%46.5%
WebDev Arena15371786

Specs and price

Claude Sonnet 5Claude Sonnet 5.5
Agent Index52.4 (#32)69 (#9)
Agent $/M$0.92$0.84
Input / output $/M$2.00 / $10.00$2.00 / $10.00
Context1M1M
ReleasedJun 30, 2026Sep 28, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Claude Sonnet 5 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