SShogo Bench

Claude Opus 4.7 vs Gemini 3.8 Flash

Gemini 3.8 Flash leads Claude Opus 4.7 by 1.6 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 4.7 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 Opus 4.7Gemini 3.8 Flash
Agentic coding6063
Long-horizon autonomy6964
Knowledge-work agents4147
Computer use4444
Security & context learning5253

Shared benchmarks

BenchmarkClaude Opus 4.7Gemini 3.8 Flash
APEX-Agentsindex49.2%64.3%
Vending-Bench 2index$10,937$5,094
ARC-AGI93.5%98.5%
ARC-AGI-275.8%89.2%
Chess Puzzles41.0%58.0%
CritPt12.0%18.3%
DTBench94.7%95.7%
FrontierCode38.5%41.2%
FrontierMath Tier 431.7%22.0%
FrontierMath Tiers 1-370.2%68.4%
GPQA Diamond90.2%95.4%
Humanity's Last Exam36.2%44.5%
LMCA52.2%52.9%
MirrorCode43.3%38.9%
OTIS Mock AIME97.8%98.9%
ProofBench54.0%48.0%
SciCode54.5%56.6%
SimpleBench61.7%82.4%
SimpleQA Verified51.7%69.7%
WebDev Arena15671568

Specs and price

Claude Opus 4.7Gemini 3.8 Flash
Agent Index54.6 (#29)56.2 (#21)
Agent $/M$2.31$0.35
Input / output $/M$5.00 / $25.00$0.75 / $3.75
Context1M1M
ReleasedApr 16, 2026Sep 2, 2026
WeightsClosedClosed
API hosts56

Don’t pick one. Route.

Shogo can run Claude Opus 4.7 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