SShogo Bench

Claude Sonnet 5.5 vs GPT-5.5

Claude Sonnet 5.5 leads GPT-5.5 by 12.3 points on the Shogo Agent Index. Claude Sonnet 5.5 wins 15 and GPT-5.5 wins 3 of 19 shared benchmarks. Claude Sonnet 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5.5GPT-5.5
Agentic coding7963
Long-horizon autonomy7567
Knowledge-work agents5746
Computer use6143
Security & context learning6155

Shared benchmarks

BenchmarkClaude Sonnet 5.5GPT-5.5
APEX-Agentsindex75.5%55.1%
Vending-Bench 2index$11,165$7,524
ARC-AGI96.5%95.0%
ARC-AGI-283.9%85.0%
Chess Puzzles59.0%63.0%
CritPt31.4%27.1%
DTBench97.3%96.0%
FrontierCode52.1%43.0%
FrontierMath Tier 480.5%72.5%
FrontierMath Tiers 1-388.8%85.3%
GPQA Diamond95.6%94.0%
LMCA68.3%54.3%
MirrorCode97.8%23.3%
OTIS Mock AIME100.0%100.0%
ProofBench100.0%50.0%
SciCode61.0%56.1%
SimpleBench75.9%69.0%
SimpleQA Verified46.5%63.0%
WebDev Arena17861510

Specs and price

Claude Sonnet 5.5GPT-5.5
Agent Index69 (#9)56.7 (#19)
Agent $/M$0.84$2.55
Input / output $/M$2.00 / $10.00$5.00 / $30.00
Context1M1.1M
ReleasedSep 28, 2026Apr 23, 2026
WeightsClosedClosed
API hosts54

Don’t pick one. Route.

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

Try both in Shogo