SShogo Bench

Claude Sonnet 5 vs Gemini 4 Argon

Gemini 4 Argon leads Claude Sonnet 5 by 17.1 points on the Shogo Agent Index. Claude Sonnet 5 wins 1 and Gemini 4 Argon wins 17 of 18 shared benchmarks. Gemini 4 Argon is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5Gemini 4 Argon
Agentic coding5777
Long-horizon autonomy6578
Knowledge-work agents4359
Computer use4061
Security & context learning5161

Shared benchmarks

BenchmarkClaude Sonnet 5Gemini 4 Argon
APEX-Agentsindex54.5%82.4%
Vending-Bench 2index$6,378$13,718
CursorBenchindex34.1%52.9%
Chess Puzzles45.0%59.0%
CritPt16.9%27.1%
DTBench92.5%97.6%
FrontierCode42.7%47.5%
FrontierMath Tier 429.3%78.0%
FrontierMath Tiers 1-365.6%86.0%
GPQA Diamond90.5%96.4%
LMCA50.0%63.7%
MirrorCode63.3%58.9%
OTIS Mock AIME94.7%100.0%
ProofBench77.0%99.0%
SciCode54.3%61.8%
SimpleBench60.6%91.7%
SimpleQA Verified33.7%76.0%
WebDev Arena15371680

Specs and price

Claude Sonnet 5Gemini 4 Argon
Agent Index52.4 (#32)69.5 (#6)
Agent $/M$0.92$0.84
Input / output $/M$2.00 / $10.00$2.00 / $10.00
Context1M1M
ReleasedJun 30, 2026Oct 13, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Claude Sonnet 5 and Gemini 4 Argon side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo