SShogo Bench

Claude Fable 5.2 vs Claude Opus 4.7

Claude Fable 5.2 leads Claude Opus 4.7 by 21.8 points on the Shogo Agent Index. Claude Fable 5.2 wins 16 and Claude Opus 4.7 wins 1 of 17 shared benchmarks. Claude Opus 4.7 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.2Claude Opus 4.7
Agentic coding8660
Long-horizon autonomy7869
Knowledge-work agents6741
Computer use7744
Security & context learning6552

Shared benchmarks

BenchmarkClaude Fable 5.2Claude Opus 4.7
APEX-Agentsindex80.1%49.2%
Vending-Bench 2index$9,628$10,937
PostTrainBenchindex44.6%24.3%
ARC-AGI98.5%93.5%
ARC-AGI-293.8%75.8%
Chess Puzzles79.0%41.0%
CritPt35.7%12.0%
DTBench99.2%94.7%
FrontierMath Tier 4100.0%31.7%
FrontierMath Tiers 1-395.1%70.2%
GPQA Diamond96.0%90.2%
LMCA70.6%52.2%
OTIS Mock AIME99.7%97.8%
ProofBench100.0%54.0%
SciCode67.7%54.5%
SimpleBench94.9%61.7%
SimpleQA Verified94.0%51.7%

Specs and price

Claude Fable 5.2Claude Opus 4.7
Agent Index76.4 (#1)54.6 (#29)
Agent $/M$3.21$2.31
Input / output $/M$8.00 / $40.00$5.00 / $25.00
Context1M1M
ReleasedNov 9, 2026Apr 16, 2026
WeightsClosedClosed
API hosts45

Don’t pick one. Route.

Shogo can run Claude Fable 5.2 and Claude Opus 4.7 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo