SShogo Bench

Claude Fable 5.2 vs GLM-5.3-Flash

Claude Fable 5.2 leads GLM-5.3-Flash by 28.1 points on the Shogo Agent Index. Claude Fable 5.2 wins 14 and GLM-5.3-Flash wins 0 of 14 shared benchmarks. GLM-5.3-Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.2GLM-5.3-Flash
Agentic coding8654
Long-horizon autonomy7857
Knowledge-work agents6740
Computer use7734
Security & context learning6547

Shared benchmarks

BenchmarkClaude Fable 5.2GLM-5.3-Flash
APEX-Agentsindex80.1%52.8%
FrontierSWEindex69.9%18.1%
CursorBenchindex60.0%36.8%
PostTrainBenchindex44.6%36.8%
ARC-AGI98.5%91.0%
ARC-AGI-293.8%65.8%
Chess Puzzles79.0%21.0%
CritPt35.7%15.4%
FrontierMath Tier 4100.0%17.1%
FrontierMath Tiers 1-395.1%55.8%
GPQA Diamond96.0%90.2%
OTIS Mock AIME99.7%93.9%
ProofBench100.0%21.0%
SciCode67.7%51.6%

Specs and price

Claude Fable 5.2GLM-5.3-Flash
Agent Index76.4 (#1)48.3 (#38)
Agent $/M$3.21$0.16
Input / output $/M$8.00 / $40.00$0.30 / $1.05
Context1M1M
ReleasedNov 9, 2026Sep 18, 2026
WeightsClosedOpen
API hosts442

Don’t pick one. Route.

Shogo can run Claude Fable 5.2 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