SShogo Bench

Claude Sonnet 5.5 vs Gemini 3.6 Flash

Claude Sonnet 5.5 leads Gemini 3.6 Flash by 20.7 points on the Shogo Agent Index. Claude Sonnet 5.5 wins 16 and Gemini 3.6 Flash wins 1 of 17 shared benchmarks. Gemini 3.6 Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5.5Gemini 3.6 Flash
Agentic coding7953
Long-horizon autonomy7558
Knowledge-work agents5739
Computer use6137
Security & context learning6149

Shared benchmarks

BenchmarkClaude Sonnet 5.5Gemini 3.6 Flash
APEX-Agentsindex75.5%46.9%
ARC-AGI96.5%91.2%
ARC-AGI-283.9%60.4%
Chess Puzzles59.0%42.0%
CritPt31.4%10.6%
DTBench97.3%95.5%
FrontierCode52.1%34.4%
FrontierMath Tier 480.5%22.0%
FrontierMath Tiers 1-388.8%58.9%
GPQA Diamond95.6%94.1%
LMCA68.3%44.9%
MirrorCode97.8%23.3%
OTIS Mock AIME100.0%94.2%
ProofBench100.0%36.0%
SciCode61.0%53.4%
SimpleQA Verified46.5%66.2%
WebDev Arena17861537

Specs and price

Claude Sonnet 5.5Gemini 3.6 Flash
Agent Index69 (#9)48.3 (#39)
Agent $/M$0.84$0.35
Input / output $/M$2.00 / $10.00$0.75 / $3.75
Context1M1M
ReleasedSep 28, 2026Jul 21, 2026
WeightsClosedClosed
API hosts56

Don’t pick one. Route.

Shogo can run Claude Sonnet 5.5 and Gemini 3.6 Flash side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo