SShogo Bench

Claude Opus 4.8 vs GPT-6.1 Terra

GPT-6.1 Terra leads Claude Opus 4.8 by 12.7 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 4.8 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 Opus 4.8GPT-6.1 Terra
Agentic coding6379
Long-horizon autonomy6674
Knowledge-work agents4356
Computer use4763
Security & context learning5562

Shared benchmarks

BenchmarkClaude Opus 4.8GPT-6.1 Terra
APEX-Agentsindex48.9%68.3%
Vending-Bench 2index$5,787$9,107
CritPt20.9%28.0%
FrontierMath Tier 456.1%92.7%
FrontierMath Tiers 1-380.0%90.9%
GPQA Diamond91.0%94.3%
MirrorCode65.6%76.7%
OTIS Mock AIME98.3%100.0%
SciCode53.5%55.1%
SimpleBench64.8%72.2%
SimpleQA Verified53.0%57.3%

Specs and price

Claude Opus 4.8GPT-6.1 Terra
Agent Index56.3 (#20)69 (#8)
Agent $/M$2.31$0.42
Input / output $/M$5.00 / $25.00$1.00 / $5.00
Context1M1.1M
ReleasedMay 28, 2026Oct 26, 2026
WeightsClosedClosed
API hosts64

Don’t pick one. Route.

Shogo can run Claude Opus 4.8 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