Which is better, Claude Fable 5 or Quasar 438B (max, based on GLM-5.2)?

Refresh Models —Deals —Regulatory —Sources —

Claude Fable 5 vs Quasar 438B (max, based on GLM-5.2)

14 SHARED BENCHMARKS

Across 14 shared benchmarks, Claude Fable 5 scores higher on 13 and Quasar 438B (max, based on GLM-5.2) on 1. The widest gap is OmniScience Accuracy, where Claude Fable 5 scores 65.3 against 15.5.

ANTHROPICVSZ.AI14 SHARED13–1 HEAD-TO-HEAD

BenchmarkClaude Fable 5MARGINQuasar 438B (max, based on GLM-5.2)

AA Agentic Index56.636.9

AA Intelligence62.143

AA-LCR76.775

AA-Omniscience43.3-2.6

Artificial Analysis Coding Index76.561.2

critpt28.69.4

gdpval61.140.9

GPQA Diamond92.673.2

HLE64.518.7

OmniScience Accuracy65.315.5

OmniScience Non-Hallucination36.478.6

scicode60.245

TauBench V3 - Banking38.128.7

Terminal-Bench 2.18869.3

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.