SShogo Bench

Claude Opus 4.8 vs Gemini 3.8 Flash

Claude Opus 4.8 leads Gemini 3.8 Flash by 0.1 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 4.8 wins 9 and Gemini 3.8 Flash wins 13 of 22 shared benchmarks. Gemini 3.8 Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.8Gemini 3.8 Flash
Agentic coding6363
Long-horizon autonomy6664
Knowledge-work agents4347
Computer use4744
Security & context learning5553

Shared benchmarks

BenchmarkClaude Opus 4.8Gemini 3.8 Flash
APEX-Agentsindex48.9%64.3%
DeepSWEindex59.0%73.8%
Vending-Bench 2index$5,787$5,094
Remote Labor Indexindex8.3%5.8%
ARC-AGI92.5%98.5%
ARC-AGI-272.1%89.2%
Chess Puzzles52.0%58.0%
CritPt20.9%18.3%
DTBench94.9%95.7%
FrontierCode46.5%41.2%
FrontierMath Tier 456.1%22.0%
FrontierMath Tiers 1-380.0%68.4%
GeoBench81.0%86.0%
GPQA Diamond91.0%95.4%
LMCA57.5%52.9%
MirrorCode65.6%38.9%
OTIS Mock AIME98.3%98.9%
ProofBench69.0%48.0%
SciCode53.5%56.6%
SimpleBench64.8%82.4%
SimpleQA Verified53.0%69.7%
WebDev Arena15591568

Specs and price

Claude Opus 4.8Gemini 3.8 Flash
Agent Index56.3 (#20)56.2 (#21)
Agent $/M$2.31$0.35
Input / output $/M$5.00 / $25.00$0.75 / $3.75
Context1M1M
ReleasedMay 28, 2026Sep 2, 2026
WeightsClosedClosed
API hosts66

Don’t pick one. Route.

Shogo can run Claude Opus 4.8 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