SShogo Bench

GPT-5.5 vs GPT-6.1 Terra

GPT-6.1 Terra leads GPT-5.5 by 12.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-5.5 wins 2 and GPT-6.1 Terra wins 8 of 11 shared benchmarks. GPT-6.1 Terra is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-5.5GPT-6.1 Terra
Agentic coding6379
Long-horizon autonomy6774
Knowledge-work agents4656
Computer use4363
Security & context learning5562

Shared benchmarks

BenchmarkGPT-5.5GPT-6.1 Terra
APEX-Agentsindex55.1%68.3%
Vending-Bench 2index$7,524$9,107
CritPt27.1%28.0%
FrontierMath Tier 472.5%92.7%
FrontierMath Tiers 1-385.3%90.9%
GPQA Diamond94.0%94.3%
MirrorCode23.3%76.7%
OTIS Mock AIME100.0%100.0%
SciCode56.1%55.1%
SimpleBench69.0%72.2%
SimpleQA Verified63.0%57.3%

Specs and price

GPT-5.5GPT-6.1 Terra
Agent Index56.7 (#19)69 (#8)
Agent $/M$2.55$0.42
Input / output $/M$5.00 / $30.00$1.00 / $5.00
Context1.1M1.1M
ReleasedApr 23, 2026Oct 26, 2026
WeightsClosedClosed
API hosts44

Don’t pick one. Route.

Shogo can run GPT-5.5 and GPT-6.1 Terra side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo