Which is better, Claude Fable 5.1 or MiniCPM5-2B?

Refresh Models —Deals —Regulatory —Sources —

Claude Fable 5.1 vs MiniCPM5-2B

15 SHARED BENCHMARKS

Across 15 shared benchmarks, Claude Fable 5.1 scores higher on 14 and MiniCPM5-2B on 1. The widest gap is OmniScience Accuracy, where Claude Fable 5.1 scores 67.2 against 8.4.

ANTHROPICVSOPENBMB15 SHARED14–1 HEAD-TO-HEAD

BenchmarkClaude Fable 5.1MARGINMiniCPM5-2B

AA Agentic Index589

AA Intelligence53.413.1

AA-LCR85.359.3

AA-Omniscience43.5-11.7

Artificial Analysis Coding Index81.614.5

critpt31.10.3

gdpval63.216.4

GPQA Diamond93.770.2

HLE658.9

OmniScience Accuracy67.28.4

OmniScience Non-Hallucination34.478.1

scicode63.126.3

TauBench V3 - Banking47.220.8

Terminal-Bench 2.191.48.6

terminalbenchV4055.10

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.