SShogo Bench

Claude Fable 5 vs GPT-6.1 Terra

GPT-6.1 Terra leads Claude Fable 5 by 4.9 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 4 and GPT-6.1 Terra wins 7 of 12 shared benchmarks. GPT-6.1 Terra is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5GPT-6.1 Terra
Agentic coding7479
Long-horizon autonomy6974
Knowledge-work agents5256
Computer use5563
Security & context learning5962

Shared benchmarks

BenchmarkClaude Fable 5GPT-6.1 Terra
APEX-Agentsindex63.6%68.3%
Vending-Bench 2index$5,680$9,107
CritPt28.6%28.0%
FrontierMath Tier 490.2%92.7%
FrontierMath Tiers 1-387.0%90.9%
GPQA Diamond93.9%94.3%
MirrorCode70.0%76.7%
OTIS Mock AIME100.0%100.0%
SciCode61.0%55.1%
SimpleBench81.9%72.2%
SimpleQA Verified70.7%57.3%
WeirdML v315.6%28.1%

Specs and price

Claude Fable 5GPT-6.1 Terra
Agent Index64.1 (#12)69 (#8)
Agent $/M$4.62$0.42
Input / output $/M$10.00 / $50.00$1.00 / $5.00
Context1M1.1M
ReleasedJun 9, 2026Oct 26, 2026
WeightsClosedClosed
API hosts44

Don’t pick one. Route.

Shogo can run Claude Fable 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