SShogo Bench

Claude Opus 4.7 vs GPT-5.6 Terra

GPT-5.6 Terra leads Claude Opus 4.7 by 4.2 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 4.7 wins 6 and GPT-5.6 Terra wins 13 of 19 shared benchmarks. GPT-5.6 Terra is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.7GPT-5.6 Terra
Agentic coding6066
Long-horizon autonomy6969
Knowledge-work agents4147
Computer use4448
Security & context learning5256

Shared benchmarks

BenchmarkClaude Opus 4.7GPT-5.6 Terra
APEX-Agentsindex49.2%58.2%
Vending-Bench 2index$10,937$7,343
ARC-AGI93.5%96.5%
ARC-AGI-275.8%83.9%
Chess Puzzles41.0%47.0%
CritPt12.0%30.0%
DTBench94.7%93.3%
FrontierCode38.5%41.3%
FrontierMath Tier 431.7%70.7%
FrontierMath Tiers 1-370.2%86.0%
GPQA Diamond90.2%93.3%
LMCA52.2%54.9%
MirrorCode43.3%41.1%
OTIS Mock AIME97.8%99.7%
ProofBench54.0%74.0%
SciCode54.5%55.0%
SimpleBench61.7%48.9%
SimpleQA Verified51.7%43.2%
WebDev Arena15671521

Specs and price

Claude Opus 4.7GPT-5.6 Terra
Agent Index54.6 (#29)58.8 (#16)
Agent $/M$2.31$1.02
Input / output $/M$5.00 / $25.00$2.00 / $12.00
Context1M1.1M
ReleasedApr 16, 2026Jul 9, 2026
WeightsClosedClosed
API hosts54

Don’t pick one. Route.

Shogo can run Claude Opus 4.7 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