AI9StarsOpen weightsReasoning modelAuto-detected

G9v3-3B

Name: G9v3-3B benchmark results
Creator: BenchLeader

Not yet ranked: too few independent results so far.

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Benchmark	default	Source
GPQA Diamond (AA)not in index	43.8%#431	Artificial Analysis
Humanity's Last Exam (AA)not in index	4.5%#419	Artificial Analysis

Benchmark	default	Source
AA-Omniscience	-4.4#114	Artificial Analysis

Benchmark	default	Source
AA-LCR	41.3%#285	Artificial Analysis

Benchmark	default	Source
AA Intelligence Index	10.8#301	Artificial Analysis