SShogo Bench

Gemini 3.7 Flash vs GPT-6 Sol

GPT-6 Sol leads Gemini 3.7 Flash by 7.9 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Gemini 3.7 Flash wins 5 and GPT-6 Sol wins 11 of 17 shared benchmarks. Gemini 3.7 Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGemini 3.7 FlashGPT-6 Sol
Agentic coding6172
Long-horizon autonomy6476
Knowledge-work agents4848
Computer use4354
Security & context learning5359

Shared benchmarks

BenchmarkGemini 3.7 FlashGPT-6 Sol
APEX-Agentsindex67.8%54.3%
ARC-AGI95.5%95.5%
ARC-AGI-284.6%89.6%
Chess Puzzles66.0%56.0%
CritPt14.3%30.9%
DTBench96.8%97.3%
FrontierCode43.6%49.3%
FrontierMath Tier 436.6%90.0%
FrontierMath Tiers 1-371.6%89.8%
GPQA Diamond94.8%94.3%
LMCA50.4%59.1%
MirrorCode41.1%48.9%
OTIS Mock AIME97.2%100.0%
ProofBench58.0%83.0%
SciCode59.8%57.6%
SimpleQA Verified69.2%60.7%
WebDev Arena15871689

Specs and price

Gemini 3.7 FlashGPT-6 Sol
Agent Index55.7 (#23)63.6 (#13)
Agent $/M$0.35$0.92
Input / output $/M$0.75 / $3.75$2.00 / $10.00
Context1M1.1M
ReleasedAug 13, 2026Sep 22, 2026
WeightsClosedClosed
API hosts65

Don’t pick one. Route.

Shogo can run Gemini 3.7 Flash 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