SShogo Bench

Claude Fable 5 vs GLM-5.3-Flash

Claude Fable 5 leads GLM-5.3-Flash by 15.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 16 and GLM-5.3-Flash wins 0 of 16 shared benchmarks. GLM-5.3-Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5GLM-5.3-Flash
Agentic coding7454
Long-horizon autonomy6957
Knowledge-work agents5240
Computer use5534
Security & context learning5947

Shared benchmarks

BenchmarkClaude Fable 5GLM-5.3-Flash
APEX-Agentsindex63.6%52.8%
DeepSWEindex69.9%63.4%
FrontierSWEindex47.0%18.1%
PostTrainBenchindex37.3%36.8%
ARC-AGI98.5%91.0%
ARC-AGI-289.2%65.8%
Chess Puzzles47.0%21.0%
CritPt28.6%15.4%
FrontierCode53.5%31.8%
FrontierMath Tier 490.2%17.1%
FrontierMath Tiers 1-387.0%55.8%
GPQA Diamond93.9%90.2%
OTIS Mock AIME100.0%93.9%
ProofBench95.0%21.0%
SciCode61.0%51.6%
WebDev Arena16281607

Specs and price

Claude Fable 5GLM-5.3-Flash
Agent Index64.1 (#12)48.3 (#38)
Agent $/M$4.62$0.16
Input / output $/M$10.00 / $50.00$0.30 / $1.05
Context1M1M
ReleasedJun 9, 2026Sep 18, 2026
WeightsClosedOpen
API hosts442

Don’t pick one. Route.

Shogo can run Claude Fable 5 and GLM-5.3-Flash side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo