SShogo Bench

Claude Haiku 5.5 vs Gemini 4 Carbon

Gemini 4 Carbon leads Claude Haiku 5.5 by 16.1 points on the Shogo Agent Index. Claude Haiku 5.5 wins 0 and Gemini 4 Carbon wins 15 of 15 shared benchmarks. Claude Haiku 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Haiku 5.5Gemini 4 Carbon
Agentic coding6782
Long-horizon autonomy6280
Knowledge-work agents4663
Computer use4768
Security & context learning5563

Shared benchmarks

BenchmarkClaude Haiku 5.5Gemini 4 Carbon
APEX-Agentsindex56.1%84.2%
Vending-Bench 2index$3,602$16,484
FrontierSWEindex43.8%61.2%
CursorBenchindex48.4%60.4%
ARC-AGI89.0%98.5%
ARC-AGI-261.3%94.2%
Chess Puzzles55.0%78.0%
CritPt22.6%36.0%
FrontierMath Tier 446.3%95.1%
FrontierMath Tiers 1-375.1%90.5%
GPQA Diamond89.6%96.5%
OTIS Mock AIME98.9%100.0%
SciCode55.0%64.2%
SimpleBench59.2%92.6%
SimpleQA Verified23.8%77.7%

Specs and price

Claude Haiku 5.5Gemini 4 Carbon
Agent Index57.5 (#18)73.6 (#2)
Agent $/M$0.050$0.84
Input / output $/M$0.10 / $0.50$2.00 / $10.00
Context1M1M
ReleasedOct 7, 2026Nov 10, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Claude Haiku 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