SShogo Bench

GPT-5.4 vs GPT-6.1 Sol

GPT-6.1 Sol leads GPT-5.4 by 18.4 points on the Shogo Agent Index. GPT-5.4 wins 1 and GPT-6.1 Sol wins 17 of 18 shared benchmarks. GPT-6.1 Sol is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-5.4GPT-6.1 Sol
Agentic coding5780
Long-horizon autonomy6178
Knowledge-work agents4054
Computer use4266
Security & context learning5462

Shared benchmarks

BenchmarkGPT-5.4GPT-6.1 Sol
APEX-Agentsindex52.4%60.0%
Vending-Bench 2index$6,144$12,861
PostTrainBenchindex17.8%38.8%
ARC-AGI93.7%98.5%
ARC-AGI-274.0%94.2%
Chess Puzzles48.0%68.0%
CritPt23.4%31.7%
DTBench94.4%96.5%
FrontierMath Tier 449.0%100.0%
FrontierMath Tiers 1-378.6%93.7%
GPQA Diamond93.3%95.4%
LMCA52.0%62.8%
MirrorCode23.3%61.1%
OTIS Mock AIME97.8%100.0%
ProofBench56.0%99.0%
SciCode56.6%55.8%
SimpleQA Verified45.1%73.9%
WebDev Arena14631759

Specs and price

GPT-5.4GPT-6.1 Sol
Agent Index51.6 (#33)70 (#5)
Agent $/M$1.27$0.84
Input / output $/M$2.50 / $15.00$2.00 / $10.00
Context1.1M1.1M
ReleasedMar 5, 2026Sep 29, 2026
WeightsClosedClosed
API hosts46

Don’t pick one. Route.

Shogo can run GPT-5.4 and GPT-6.1 Sol side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo