SShogo Bench

Claude Opus 5 vs Gemini 4 Argon

Gemini 4 Argon leads Claude Opus 5 by 4.1 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 5 wins 6 and Gemini 4 Argon wins 16 of 23 shared benchmarks. Gemini 4 Argon is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 5Gemini 4 Argon
Agentic coding7477
Long-horizon autonomy7478
Knowledge-work agents5259
Computer use5661
Security & context learning5961

Shared benchmarks

BenchmarkClaude Opus 5Gemini 4 Argon
APEX-Agentsindex65.8%82.4%
Vending-Bench 2index$11,182$13,718
FrontierSWEindex52.0%55.0%
CursorBenchindex46.6%52.9%
PostTrainBenchindex35.7%40.4%
ARC-AGI97.5%98.5%
ARC-AGI-290.4%91.3%
Chess Puzzles43.0%59.0%
CritPt29.1%27.1%
DTBench97.9%97.6%
FrontierCode53.4%47.5%
FrontierMath Tier 473.2%78.0%
FrontierMath Tiers 1-385.6%86.0%
GPQA Diamond93.9%96.4%
LMCA64.5%63.7%
MirrorCode87.8%58.9%
OTIS Mock AIME98.9%100.0%
ProofBench99.0%99.0%
SciCode56.4%61.8%
SimpleBench80.6%91.7%
SimpleQA Verified59.9%76.0%
WebDev Arena16871680
WeirdML v319.0%20.3%

Specs and price

Claude Opus 5Gemini 4 Argon
Agent Index65.4 (#11)69.5 (#6)
Agent $/M$2.31$0.84
Input / output $/M$5.00 / $25.00$2.00 / $10.00
Context1M1M
ReleasedJul 24, 2026Oct 13, 2026
WeightsClosedClosed
API hosts65

Don’t pick one. Route.

Shogo can run Claude Opus 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