SShogo Bench

Claude Fable 5.2 vs GPT-6.1 Terra

Claude Fable 5.2 leads GPT-6.1 Terra by 7.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5.2 wins 10 and GPT-6.1 Terra wins 1 of 11 shared benchmarks. GPT-6.1 Terra is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.2GPT-6.1 Terra
Agentic coding8679
Long-horizon autonomy7874
Knowledge-work agents6756
Computer use7763
Security & context learning6562

Shared benchmarks

BenchmarkClaude Fable 5.2GPT-6.1 Terra
APEX-Agentsindex80.1%68.3%
Vending-Bench 2index$9,628$9,107
CritPt35.7%28.0%
FrontierMath Tier 4100.0%92.7%
FrontierMath Tiers 1-395.1%90.9%
GPQA Diamond96.0%94.3%
OTIS Mock AIME99.7%100.0%
SciCode67.7%55.1%
SimpleBench94.9%72.2%
SimpleQA Verified94.0%57.3%
WeirdML v343.1%28.1%

Specs and price

Claude Fable 5.2GPT-6.1 Terra
Agent Index76.4 (#1)69 (#8)
Agent $/M$3.21$0.42
Input / output $/M$8.00 / $40.00$1.00 / $5.00
Context1M1.1M
ReleasedNov 9, 2026Oct 26, 2026
WeightsClosedClosed
API hosts44

Don’t pick one. Route.

Shogo can run Claude Fable 5.2 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