SShogo Bench

Claude Sonnet 5 vs GPT-6.1 Terra

GPT-6.1 Terra leads Claude Sonnet 5 by 16.6 points on the Shogo Agent Index. Claude Sonnet 5 wins 0 and GPT-6.1 Terra wins 11 of 11 shared benchmarks. GPT-6.1 Terra is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5GPT-6.1 Terra
Agentic coding5779
Long-horizon autonomy6574
Knowledge-work agents4356
Computer use4063
Security & context learning5162

Shared benchmarks

BenchmarkClaude Sonnet 5GPT-6.1 Terra
APEX-Agentsindex54.5%68.3%
Vending-Bench 2index$6,378$9,107
CritPt16.9%28.0%
FrontierMath Tier 429.3%92.7%
FrontierMath Tiers 1-365.6%90.9%
GPQA Diamond90.5%94.3%
MirrorCode63.3%76.7%
OTIS Mock AIME94.7%100.0%
SciCode54.3%55.1%
SimpleBench60.6%72.2%
SimpleQA Verified33.7%57.3%

Specs and price

Claude Sonnet 5GPT-6.1 Terra
Agent Index52.4 (#32)69 (#8)
Agent $/M$0.92$0.42
Input / output $/M$2.00 / $10.00$1.00 / $5.00
Context1M1.1M
ReleasedJun 30, 2026Oct 26, 2026
WeightsClosedClosed
API hosts54

Don’t pick one. Route.

Shogo can run Claude Sonnet 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