SShogo Bench

Claude Opus 4.6 vs GPT-5.6 Terra

GPT-5.6 Terra leads Claude Opus 4.6 by 5.6 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 4.6 wins 5 and GPT-5.6 Terra wins 12 of 17 shared benchmarks. GPT-5.6 Terra is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.6GPT-5.6 Terra
Agentic coding5766
Long-horizon autonomy6769
Knowledge-work agents4147
Computer use3948
Security & context learning5756

Shared benchmarks

BenchmarkClaude Opus 4.6GPT-5.6 Terra
APEX-Agentsindex46.3%58.2%
Vending-Bench 2index$8,018$7,343
ARC-AGI94.0%96.5%
ARC-AGI-269.2%83.9%
Chess Puzzles21.0%47.0%
DTBench91.2%93.3%
FrontierCode26.6%41.3%
FrontierMath Tier 426.8%70.7%
FrontierMath Tiers 1-366.0%86.0%
GPQA Diamond90.5%93.3%
LMCA55.8%54.9%
MirrorCode33.3%41.1%
OTIS Mock AIME94.4%99.7%
ProofBench50.0%74.0%
SimpleBench67.6%48.9%
SimpleQA Verified47.0%43.2%
WebDev Arena15561521

Specs and price

Claude Opus 4.6GPT-5.6 Terra
Agent Index53.2 (#31)58.8 (#16)
Agent $/M$2.31$1.02
Input / output $/M$5.00 / $25.00$2.00 / $12.00
Context1M1.1M
ReleasedFeb 5, 2026Jul 9, 2026
WeightsClosedClosed
API hosts54

Don’t pick one. Route.

Shogo can run Claude Opus 4.6 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