SShogo Bench

Claude Opus 4.6 vs Gemini 4 Argon

Gemini 4 Argon leads Claude Opus 4.6 by 16.3 points on the Shogo Agent Index. Claude Opus 4.6 wins 0 and Gemini 4 Argon wins 18 of 18 shared benchmarks. Gemini 4 Argon is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.6Gemini 4 Argon
Agentic coding5777
Long-horizon autonomy6778
Knowledge-work agents4159
Computer use3961
Security & context learning5761

Shared benchmarks

BenchmarkClaude Opus 4.6Gemini 4 Argon
APEX-Agentsindex46.3%82.4%
Vending-Bench 2index$8,018$13,718
Remote Labor Indexindex4.2%17.1%
ARC-AGI94.0%98.5%
ARC-AGI-269.2%91.3%
Chess Puzzles21.0%59.0%
DTBench91.2%97.6%
FrontierCode26.6%47.5%
FrontierMath Tier 426.8%78.0%
FrontierMath Tiers 1-366.0%86.0%
GPQA Diamond90.5%96.4%
LMCA55.8%63.7%
MirrorCode33.3%58.9%
OTIS Mock AIME94.4%100.0%
ProofBench50.0%99.0%
SimpleBench67.6%91.7%
SimpleQA Verified47.0%76.0%
WebDev Arena15561680

Specs and price

Claude Opus 4.6Gemini 4 Argon
Agent Index53.2 (#31)69.5 (#6)
Agent $/M$2.31$0.84
Input / output $/M$5.00 / $25.00$2.00 / $10.00
Context1M1M
ReleasedFeb 5, 2026Oct 13, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Claude Opus 4.6 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