SShogo Bench

Claude Sonnet 5.5 vs Gemini 4 Argon

Gemini 4 Argon leads Claude Sonnet 5.5 by 0.5 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Sonnet 5.5 wins 10 and Gemini 4 Argon wins 10 of 22 shared benchmarks. Claude Sonnet 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5.5Gemini 4 Argon
Agentic coding7977
Long-horizon autonomy7578
Knowledge-work agents5759
Computer use6161
Security & context learning6161

Shared benchmarks

BenchmarkClaude Sonnet 5.5Gemini 4 Argon
APEX-Agentsindex75.5%82.4%
Vending-Bench 2index$11,165$13,718
FrontierSWEindex61.9%55.0%
CursorBenchindex55.5%52.9%
ARC-AGI96.5%98.5%
ARC-AGI-283.9%91.3%
Chess Puzzles59.0%59.0%
CritPt31.4%27.1%
DTBench97.3%97.6%
FrontierCode52.1%47.5%
FrontierMath Tier 480.5%78.0%
FrontierMath Tiers 1-388.8%86.0%
GPQA Diamond95.6%96.4%
LMCA68.3%63.7%
MirrorCode97.8%58.9%
OTIS Mock AIME100.0%100.0%
ProofBench100.0%99.0%
SciCode61.0%61.8%
SimpleBench75.9%91.7%
SimpleQA Verified46.5%76.0%
WebDev Arena17861680
WeirdML v319.9%20.3%

Specs and price

Claude Sonnet 5.5Gemini 4 Argon
Agent Index69 (#9)69.5 (#6)
Agent $/M$0.84$0.84
Input / output $/M$2.00 / $10.00$2.00 / $10.00
Context1M1M
ReleasedSep 28, 2026Oct 13, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Claude Sonnet 5.5 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