SShogo Bench

Claude Haiku 5.5 vs GPT-5.6 Terra

GPT-5.6 Terra leads Claude Haiku 5.5 by 1.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Haiku 5.5 wins 7 and GPT-5.6 Terra wins 11 of 19 shared benchmarks. Claude Haiku 5.5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Haiku 5.5GPT-5.6 Terra
Agentic coding6766
Long-horizon autonomy6269
Knowledge-work agents4647
Computer use4748
Security & context learning5556

Shared benchmarks

BenchmarkClaude Haiku 5.5GPT-5.6 Terra
APEX-Agentsindex56.1%58.2%
Vending-Bench 2index$3,602$7,343
CursorBenchindex48.4%41.3%
ARC-AGI89.0%96.5%
ARC-AGI-261.3%83.9%
Chess Puzzles55.0%47.0%
CritPt22.6%30.0%
DTBench95.0%93.3%
FrontierCode46.4%41.3%
FrontierMath Tier 446.3%70.7%
FrontierMath Tiers 1-375.1%86.0%
GPQA Diamond89.6%93.3%
LMCA51.1%54.9%
MirrorCode78.9%41.1%
OTIS Mock AIME98.9%99.7%
ProofBench89.0%74.0%
SciCode55.0%55.0%
SimpleBench59.2%48.9%
SimpleQA Verified23.8%43.2%

Specs and price

Claude Haiku 5.5GPT-5.6 Terra
Agent Index57.5 (#18)58.8 (#16)
Agent $/M$0.050$1.02
Input / output $/M$0.10 / $0.50$2.00 / $12.00
Context1M1.1M
ReleasedOct 7, 2026Jul 9, 2026
WeightsClosedClosed
API hosts54

Don’t pick one. Route.

Shogo can run Claude Haiku 5.5 and GPT-5.6 Terra side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo