SShogo Bench

Claude Sonnet 5.5 vs GPT-6 Sol

Claude Sonnet 5.5 leads GPT-6 Sol by 5.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Sonnet 5.5 wins 13 and GPT-6 Sol wins 5 of 20 shared benchmarks. Claude Sonnet 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5.5GPT-6 Sol
Agentic coding7972
Long-horizon autonomy7576
Knowledge-work agents5748
Computer use6154
Security & context learning6159

Shared benchmarks

BenchmarkClaude Sonnet 5.5GPT-6 Sol
APEX-Agentsindex75.5%54.3%
Vending-Bench 2index$11,165$14,428
ARC-AGI96.5%95.5%
ARC-AGI-283.9%89.6%
Chess Puzzles59.0%56.0%
CritPt31.4%30.9%
DTBench97.3%97.3%
FrontierCode52.1%49.3%
FrontierMath Tier 480.5%90.0%
FrontierMath Tiers 1-388.8%89.8%
GPQA Diamond95.6%94.3%
LMCA68.3%59.1%
MirrorCode97.8%48.9%
OTIS Mock AIME100.0%100.0%
ProofBench100.0%83.0%
SciCode61.0%57.6%
SimpleBench75.9%73.1%
SimpleQA Verified46.5%60.7%
WebDev Arena17861689
WeirdML v319.9%19.7%

Specs and price

Claude Sonnet 5.5GPT-6 Sol
Agent Index69 (#9)63.6 (#13)
Agent $/M$0.84$0.92
Input / output $/M$2.00 / $10.00$2.00 / $10.00
Context1M1.1M
ReleasedSep 28, 2026Sep 22, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Claude Sonnet 5.5 and GPT-6 Sol side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo