SShogo Bench

Claude Fable 5.2 vs GPT-5.6 Terra

Claude Fable 5.2 leads GPT-5.6 Terra by 17.6 points on the Shogo Agent Index. Claude Fable 5.2 wins 16 and GPT-5.6 Terra wins 0 of 17 shared benchmarks. GPT-5.6 Terra is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.2GPT-5.6 Terra
Agentic coding8666
Long-horizon autonomy7869
Knowledge-work agents6747
Computer use7748
Security & context learning6556

Shared benchmarks

BenchmarkClaude Fable 5.2GPT-5.6 Terra
APEX-Agentsindex80.1%58.2%
Vending-Bench 2index$9,628$7,343
CursorBenchindex60.0%41.3%
ARC-AGI98.5%96.5%
ARC-AGI-293.8%83.9%
Chess Puzzles79.0%47.0%
CritPt35.7%30.0%
DTBench99.2%93.3%
FrontierMath Tier 4100.0%70.7%
FrontierMath Tiers 1-395.1%86.0%
GPQA Diamond96.0%93.3%
LMCA70.6%54.9%
OTIS Mock AIME99.7%99.7%
ProofBench100.0%74.0%
SciCode67.7%55.0%
SimpleBench94.9%48.9%
SimpleQA Verified94.0%43.2%

Specs and price

Claude Fable 5.2GPT-5.6 Terra
Agent Index76.4 (#1)58.8 (#16)
Agent $/M$3.21$1.02
Input / output $/M$8.00 / $40.00$2.00 / $12.00
Context1M1.1M
ReleasedNov 9, 2026Jul 9, 2026
WeightsClosedClosed
API hosts44

Don’t pick one. Route.

Shogo can run Claude Fable 5.2 and GPT-5.6 Terra side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo