SShogo Bench

GPT-5.4 vs GPT-6 Sol

GPT-6 Sol leads GPT-5.4 by 12.0 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-5.4 wins 0 and GPT-6 Sol wins 17 of 17 shared benchmarks. GPT-6 Sol is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-5.4GPT-6 Sol
Agentic coding5772
Long-horizon autonomy6176
Knowledge-work agents4048
Computer use4254
Security & context learning5459

Shared benchmarks

BenchmarkGPT-5.4GPT-6 Sol
APEX-Agentsindex52.4%54.3%
Vending-Bench 2index$6,144$14,428
ARC-AGI93.7%95.5%
ARC-AGI-274.0%89.6%
Chess Puzzles48.0%56.0%
CritPt23.4%30.9%
DTBench94.4%97.3%
FrontierMath Tier 449.0%90.0%
FrontierMath Tiers 1-378.6%89.8%
GPQA Diamond93.3%94.3%
LMCA52.0%59.1%
MirrorCode23.3%48.9%
OTIS Mock AIME97.8%100.0%
ProofBench56.0%83.0%
SciCode56.6%57.6%
SimpleQA Verified45.1%60.7%
WebDev Arena14631689

Specs and price

GPT-5.4GPT-6 Sol
Agent Index51.6 (#33)63.6 (#13)
Agent $/M$1.27$0.92
Input / output $/M$2.50 / $15.00$2.00 / $10.00
Context1.1M1.1M
ReleasedMar 5, 2026Sep 22, 2026
WeightsClosedClosed
API hosts45

Don’t pick one. Route.

Shogo can run GPT-5.4 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