SShogo Bench

Gemini 4 Argon vs GPT-6 Sol

Gemini 4 Argon leads GPT-6 Sol by 5.9 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Gemini 4 Argon wins 13 and GPT-6 Sol wins 6 of 20 shared benchmarks. Gemini 4 Argon is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGemini 4 ArgonGPT-6 Sol
Agentic coding7772
Long-horizon autonomy7876
Knowledge-work agents5948
Computer use6154
Security & context learning6159

Shared benchmarks

BenchmarkGemini 4 ArgonGPT-6 Sol
APEX-Agentsindex82.4%54.3%
Vending-Bench 2index$13,718$14,428
ARC-AGI98.5%95.5%
ARC-AGI-291.3%89.6%
Chess Puzzles59.0%56.0%
CritPt27.1%30.9%
DTBench97.6%97.3%
FrontierCode47.5%49.3%
FrontierMath Tier 478.0%90.0%
FrontierMath Tiers 1-386.0%89.8%
GPQA Diamond96.4%94.3%
LMCA63.7%59.1%
MirrorCode58.9%48.9%
OTIS Mock AIME100.0%100.0%
ProofBench99.0%83.0%
SciCode61.8%57.6%
SimpleBench91.7%73.1%
SimpleQA Verified76.0%60.7%
WebDev Arena16801689
WeirdML v320.3%19.7%

Specs and price

Gemini 4 ArgonGPT-6 Sol
Agent Index69.5 (#6)63.6 (#13)
Agent $/M$0.84$0.92
Input / output $/M$2.00 / $10.00$2.00 / $10.00
Context1M1.1M
ReleasedOct 13, 2026Sep 22, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Gemini 4 Argon 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