SShogo Bench

Claude Sonnet 5 vs Gemini 3.7 Flash

Gemini 3.7 Flash leads Claude Sonnet 5 by 3.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Sonnet 5 wins 3 and Gemini 3.7 Flash wins 13 of 16 shared benchmarks. Gemini 3.7 Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5Gemini 3.7 Flash
Agentic coding5761
Long-horizon autonomy6564
Knowledge-work agents4348
Computer use4043
Security & context learning5153

Shared benchmarks

BenchmarkClaude Sonnet 5Gemini 3.7 Flash
APEX-Agentsindex54.5%67.8%
DeepSWEindex53.8%65.5%
Chess Puzzles45.0%66.0%
CritPt16.9%14.3%
DTBench92.5%96.8%
FrontierCode42.7%43.6%
FrontierMath Tier 429.3%36.6%
FrontierMath Tiers 1-365.6%71.6%
GPQA Diamond90.5%94.8%
LMCA50.0%50.4%
MirrorCode63.3%41.1%
OTIS Mock AIME94.7%97.2%
ProofBench77.0%58.0%
SciCode54.3%59.8%
SimpleQA Verified33.7%69.2%
WebDev Arena15371587

Specs and price

Claude Sonnet 5Gemini 3.7 Flash
Agent Index52.4 (#32)55.7 (#23)
Agent $/M$0.92$0.35
Input / output $/M$2.00 / $10.00$0.75 / $3.75
Context1M1M
ReleasedJun 30, 2026Aug 13, 2026
WeightsClosedClosed
API hosts56

Don’t pick one. Route.

Shogo can run Claude Sonnet 5 and Gemini 3.7 Flash side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo