SShogo Bench

Claude Opus 4.7 vs Gemini 4 Argon

Gemini 4 Argon leads Claude Opus 4.7 by 14.9 points on the Shogo Agent Index. Claude Opus 4.7 wins 0 and Gemini 4 Argon wins 20 of 20 shared benchmarks. Gemini 4 Argon is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.7Gemini 4 Argon
Agentic coding6077
Long-horizon autonomy6978
Knowledge-work agents4159
Computer use4461
Security & context learning5261

Shared benchmarks

BenchmarkClaude Opus 4.7Gemini 4 Argon
APEX-Agentsindex49.2%82.4%
Vending-Bench 2index$10,937$13,718
PostTrainBenchindex24.3%40.4%
ARC-AGI93.5%98.5%
ARC-AGI-275.8%91.3%
Chess Puzzles41.0%59.0%
CritPt12.0%27.1%
DTBench94.7%97.6%
FrontierCode38.5%47.5%
FrontierMath Tier 431.7%78.0%
FrontierMath Tiers 1-370.2%86.0%
GPQA Diamond90.2%96.4%
LMCA52.2%63.7%
MirrorCode43.3%58.9%
OTIS Mock AIME97.8%100.0%
ProofBench54.0%99.0%
SciCode54.5%61.8%
SimpleBench61.7%91.7%
SimpleQA Verified51.7%76.0%
WebDev Arena15671680

Specs and price

Claude Opus 4.7Gemini 4 Argon
Agent Index54.6 (#29)69.5 (#6)
Agent $/M$2.31$0.84
Input / output $/M$5.00 / $25.00$2.00 / $10.00
Context1M1M
ReleasedApr 16, 2026Oct 13, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Claude Opus 4.7 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