SShogo Bench

Claude Fable 5.2 vs Claude Opus 5

Claude Fable 5.2 leads Claude Opus 5 by 11.0 points on the Shogo Agent Index. Claude Fable 5.2 wins 19 and Claude Opus 5 wins 1 of 20 shared benchmarks. Claude Opus 5 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.2Claude Opus 5
Agentic coding8674
Long-horizon autonomy7874
Knowledge-work agents6752
Computer use7756
Security & context learning6559

Shared benchmarks

BenchmarkClaude Fable 5.2Claude Opus 5
APEX-Agentsindex80.1%65.8%
Vending-Bench 2index$9,628$11,182
FrontierSWEindex69.9%52.0%
CursorBenchindex60.0%46.6%
PostTrainBenchindex44.6%35.7%
ARC-AGI98.5%97.5%
ARC-AGI-293.8%90.4%
Chess Puzzles79.0%43.0%
CritPt35.7%29.1%
DTBench99.2%97.9%
FrontierMath Tier 4100.0%73.2%
FrontierMath Tiers 1-395.1%85.6%
GPQA Diamond96.0%93.9%
LMCA70.6%64.5%
OTIS Mock AIME99.7%98.9%
ProofBench100.0%99.0%
SciCode67.7%56.4%
SimpleBench94.9%80.6%
SimpleQA Verified94.0%59.9%
WeirdML v343.1%19.0%

Specs and price

Claude Fable 5.2Claude Opus 5
Agent Index76.4 (#1)65.4 (#11)
Agent $/M$3.21$2.31
Input / output $/M$8.00 / $40.00$5.00 / $25.00
Context1M1M
ReleasedNov 9, 2026Jul 24, 2026
WeightsClosedClosed
API hosts46

Don’t pick one. Route.

Shogo can run Claude Fable 5.2 and Claude Opus 5 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo