SShogo Bench

Claude Opus 4.6 vs Claude Sonnet 5.5

Claude Sonnet 5.5 leads Claude Opus 4.6 by 15.8 points on the Shogo Agent Index. Claude Opus 4.6 wins 1 and Claude Sonnet 5.5 wins 17 of 18 shared benchmarks. Claude Sonnet 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.6Claude Sonnet 5.5
Agentic coding5779
Long-horizon autonomy6775
Knowledge-work agents4157
Computer use3961
Security & context learning5761

Shared benchmarks

BenchmarkClaude Opus 4.6Claude Sonnet 5.5
APEX-Agentsindex46.3%75.5%
Vending-Bench 2index$8,018$11,165
ARC-AGI94.0%96.5%
ARC-AGI-269.2%83.9%
Chess Puzzles21.0%59.0%
DTBench91.2%97.3%
FrontierCode26.6%52.1%
FrontierMath Tier 426.8%80.5%
FrontierMath Tiers 1-366.0%88.8%
GPQA Diamond90.5%95.6%
Humanity's Last Exam34.4%46.1%
LMCA55.8%68.3%
MirrorCode33.3%97.8%
OTIS Mock AIME94.4%100.0%
ProofBench50.0%100.0%
SimpleBench67.6%75.9%
SimpleQA Verified47.0%46.5%
WebDev Arena15561786

Specs and price

Claude Opus 4.6Claude Sonnet 5.5
Agent Index53.2 (#31)69 (#9)
Agent $/M$2.31$0.84
Input / output $/M$5.00 / $25.00$2.00 / $10.00
Context1M1M
ReleasedFeb 5, 2026Sep 28, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Claude Opus 4.6 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