SShogo Bench

GPT-5.5 vs GPT-6 Sol

GPT-6 Sol leads GPT-5.5 by 6.9 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-5.5 wins 3 and GPT-6 Sol wins 15 of 19 shared benchmarks. GPT-6 Sol is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-5.5GPT-6 Sol
Agentic coding6372
Long-horizon autonomy6776
Knowledge-work agents4648
Computer use4354
Security & context learning5559

Shared benchmarks

BenchmarkGPT-5.5GPT-6 Sol
APEX-Agentsindex55.1%54.3%
Vending-Bench 2index$7,524$14,428
ARC-AGI95.0%95.5%
ARC-AGI-285.0%89.6%
Chess Puzzles63.0%56.0%
CritPt27.1%30.9%
DTBench96.0%97.3%
FrontierCode43.0%49.3%
FrontierMath Tier 472.5%90.0%
FrontierMath Tiers 1-385.3%89.8%
GPQA Diamond94.0%94.3%
LMCA54.3%59.1%
MirrorCode23.3%48.9%
OTIS Mock AIME100.0%100.0%
ProofBench50.0%83.0%
SciCode56.1%57.6%
SimpleBench69.0%73.1%
SimpleQA Verified63.0%60.7%
WebDev Arena15101689

Specs and price

GPT-5.5GPT-6 Sol
Agent Index56.7 (#19)63.6 (#13)
Agent $/M$2.55$0.92
Input / output $/M$5.00 / $30.00$2.00 / $10.00
Context1.1M1.1M
ReleasedApr 23, 2026Sep 22, 2026
WeightsClosedClosed
API hosts45

Don’t pick one. Route.

Shogo can run GPT-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