Which is better, Claude Fable 5 or K2 Horizon 375B A23B?

Refresh Models —Deals —Regulatory —Sources —

Claude Fable 5 vs K2 Horizon 375B A23B

14 SHARED BENCHMARKS

Across 14 shared benchmarks, Claude Fable 5 scores higher on 13 and K2 Horizon 375B A23B on 1. The widest gap is critpt, where Claude Fable 5 scores 28.6 against 4.6.

ANTHROPICVSMOONSHOT14 SHARED13–1 HEAD-TO-HEAD

BenchmarkClaude Fable 5MARGINK2 Horizon 375B A23B

AA Agentic Index56.642.8

AA Intelligence62.147.3

AA-LCR76.775.7

AA-Omniscience43.3-3

Artificial Analysis Coding Index76.561.5

critpt28.64.6

gdpval61.146.2

GPQA Diamond92.687.3

HLE64.532

OmniScience Accuracy65.318.2

OmniScience Non-Hallucination36.474.1

scicode60.240.7

TauBench V3 - Banking38.134.2

Terminal-Bench 2.18871.9

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.