SShogo Bench

Claude Sonnet 5.5 vs Gemini 4 Carbon

Gemini 4 Carbon leads Claude Sonnet 5.5 by 4.6 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Sonnet 5.5 wins 1 and Gemini 4 Carbon wins 13 of 15 shared benchmarks. Claude Sonnet 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5.5Gemini 4 Carbon
Agentic coding7982
Long-horizon autonomy7580
Knowledge-work agents5763
Computer use6168
Security & context learning6163

Shared benchmarks

BenchmarkClaude Sonnet 5.5Gemini 4 Carbon
APEX-Agentsindex75.5%84.2%
Vending-Bench 2index$11,165$16,484
FrontierSWEindex61.9%61.2%
CursorBenchindex55.5%60.4%
ARC-AGI96.5%98.5%
ARC-AGI-283.9%94.2%
Chess Puzzles59.0%78.0%
CritPt31.4%36.0%
FrontierMath Tier 480.5%95.1%
FrontierMath Tiers 1-388.8%90.5%
GPQA Diamond95.6%96.5%
OTIS Mock AIME100.0%100.0%
SciCode61.0%64.2%
SimpleBench75.9%92.6%
SimpleQA Verified46.5%77.7%

Specs and price

Claude Sonnet 5.5Gemini 4 Carbon
Agent Index69 (#9)73.6 (#2)
Agent $/M$0.84$0.84
Input / output $/M$2.00 / $10.00$2.00 / $10.00
Context1M1M
ReleasedSep 28, 2026Nov 10, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Claude Sonnet 5.5 and Gemini 4 Carbon side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo