SShogo Bench

Claude Haiku 5.5 vs Gemini 4 Argon

Gemini 4 Argon leads Claude Haiku 5.5 by 12.0 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Haiku 5.5 wins 1 and Gemini 4 Argon wins 20 of 21 shared benchmarks. Claude Haiku 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Haiku 5.5Gemini 4 Argon
Agentic coding6777
Long-horizon autonomy6278
Knowledge-work agents4659
Computer use4761
Security & context learning5561

Shared benchmarks

BenchmarkClaude Haiku 5.5Gemini 4 Argon
APEX-Agentsindex56.1%82.4%
Vending-Bench 2index$3,602$13,718
FrontierSWEindex43.8%55.0%
CursorBenchindex48.4%52.9%
ARC-AGI89.0%98.5%
ARC-AGI-261.3%91.3%
Chess Puzzles55.0%59.0%
CritPt22.6%27.1%
DTBench95.0%97.6%
FrontierCode46.4%47.5%
FrontierMath Tier 446.3%78.0%
FrontierMath Tiers 1-375.1%86.0%
GPQA Diamond89.6%96.4%
LMCA51.1%63.7%
MirrorCode78.9%58.9%
OTIS Mock AIME98.9%100.0%
ProofBench89.0%99.0%
SciCode55.0%61.8%
SimpleBench59.2%91.7%
SimpleQA Verified23.8%76.0%
WeirdML v311.7%20.3%

Specs and price

Claude Haiku 5.5Gemini 4 Argon
Agent Index57.5 (#18)69.5 (#6)
Agent $/M$0.050$0.84
Input / output $/M$0.10 / $0.50$2.00 / $10.00
Context1M1M
ReleasedOct 7, 2026Oct 13, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Claude Haiku 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