SShogo Bench

Claude Sonnet 5.5 vs Gemini 3.8 Flash

Claude Sonnet 5.5 leads Gemini 3.8 Flash by 12.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Sonnet 5.5 wins 19 and Gemini 3.8 Flash wins 4 of 23 shared benchmarks. Gemini 3.8 Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5.5Gemini 3.8 Flash
Agentic coding7963
Long-horizon autonomy7564
Knowledge-work agents5747
Computer use6144
Security & context learning6153

Shared benchmarks

BenchmarkClaude Sonnet 5.5Gemini 3.8 Flash
APEX-Agentsindex75.5%64.3%
Vending-Bench 2index$11,165$5,094
FrontierSWEindex61.9%19.6%
CursorBenchindex55.5%39.6%
ARC-AGI96.5%98.5%
ARC-AGI-283.9%89.2%
Chess Puzzles59.0%58.0%
CritPt31.4%18.3%
DTBench97.3%95.7%
FrontierCode52.1%41.2%
FrontierMath Tier 480.5%22.0%
FrontierMath Tiers 1-388.8%68.4%
GPQA Diamond95.6%95.4%
Humanity's Last Exam46.1%44.5%
LMCA68.3%52.9%
MirrorCode97.8%38.9%
OTIS Mock AIME100.0%98.9%
ProofBench100.0%48.0%
SciCode61.0%56.6%
SimpleBench75.9%82.4%
SimpleQA Verified46.5%69.7%
WebDev Arena17861568
WeirdML v319.9%7.4%

Specs and price

Claude Sonnet 5.5Gemini 3.8 Flash
Agent Index69 (#9)56.2 (#21)
Agent $/M$0.84$0.35
Input / output $/M$2.00 / $10.00$0.75 / $3.75
Context1M1M
ReleasedSep 28, 2026Sep 2, 2026
WeightsClosedClosed
API hosts56

Don’t pick one. Route.

Shogo can run Claude Sonnet 5.5 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