SShogo Bench

Claude Sonnet 5 vs Gemini 3.8 Flash

Gemini 3.8 Flash leads Claude Sonnet 5 by 3.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Sonnet 5 wins 5 and Gemini 3.8 Flash wins 15 of 20 shared benchmarks. Gemini 3.8 Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5Gemini 3.8 Flash
Agentic coding5763
Long-horizon autonomy6564
Knowledge-work agents4347
Computer use4044
Security & context learning5153

Shared benchmarks

BenchmarkClaude Sonnet 5Gemini 3.8 Flash
APEX-Agentsindex54.5%64.3%
DeepSWEindex53.8%73.8%
Vending-Bench 2index$6,378$5,094
CursorBenchindex34.1%39.6%
Chess Puzzles45.0%58.0%
CritPt16.9%18.3%
DTBench92.5%95.7%
FrontierCode42.7%41.2%
FrontierMath Tier 429.3%22.0%
FrontierMath Tiers 1-365.6%68.4%
GeoBench74.0%86.0%
GPQA Diamond90.5%95.4%
LMCA50.0%52.9%
MirrorCode63.3%38.9%
OTIS Mock AIME94.7%98.9%
ProofBench77.0%48.0%
SciCode54.3%56.6%
SimpleBench60.6%82.4%
SimpleQA Verified33.7%69.7%
WebDev Arena15371568

Specs and price

Claude Sonnet 5Gemini 3.8 Flash
Agent Index52.4 (#32)56.2 (#21)
Agent $/M$0.92$0.35
Input / output $/M$2.00 / $10.00$0.75 / $3.75
Context1M1M
ReleasedJun 30, 2026Sep 2, 2026
WeightsClosedClosed
API hosts56

Don’t pick one. Route.

Shogo can run Claude Sonnet 5 and Gemini 3.8 Flash side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo