SShogo Bench

Gemini 3.7 Flash vs GPT-5.5

GPT-5.5 leads Gemini 3.7 Flash by 1.0 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Gemini 3.7 Flash wins 11 and GPT-5.5 wins 8 of 19 shared benchmarks. Gemini 3.7 Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGemini 3.7 FlashGPT-5.5
Agentic coding6163
Long-horizon autonomy6467
Knowledge-work agents4846
Computer use4343
Security & context learning5355

Shared benchmarks

BenchmarkGemini 3.7 FlashGPT-5.5
APEX-Agentsindex67.8%55.1%
DeepSWEindex65.5%67.0%
Remote Labor Indexindex5.0%6.3%
ARC-AGI95.5%95.0%
ARC-AGI-284.6%85.0%
Chess Puzzles66.0%63.0%
CritPt14.3%27.1%
DTBench96.8%96.0%
FrontierCode43.6%43.0%
FrontierMath Tier 436.6%72.5%
FrontierMath Tiers 1-371.6%85.3%
GPQA Diamond94.8%94.0%
LMCA50.4%54.3%
MirrorCode41.1%23.3%
OTIS Mock AIME97.2%100.0%
ProofBench58.0%50.0%
SciCode59.8%56.1%
SimpleQA Verified69.2%63.0%
WebDev Arena15871510

Specs and price

Gemini 3.7 FlashGPT-5.5
Agent Index55.7 (#23)56.7 (#19)
Agent $/M$0.35$2.55
Input / output $/M$0.75 / $3.75$5.00 / $30.00
Context1M1.1M
ReleasedAug 13, 2026Apr 23, 2026
WeightsClosedClosed
API hosts64

Don’t pick one. Route.

Shogo can run Gemini 3.7 Flash and GPT-5.5 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo