NOVA-63 Benchmark Leaderboard | Phaseo

NOVA-63

AI benchmark results and model performance

Type: percentageGeneral

Recorded Results

10

Average Score

54.79%

Score Range

42.40% - 59.10%

Leading Model (lowest score)

42.40% - Qwen 3.5 0.8B

Scores Over Time

Individual benchmark scores plotted by date.

Models Using This Benchmark

Organisation	Model	Reported	Top Score	Info	Self Reported	Source
Qwen	Qwen 3.5 0.8B	02 Mar 2026	42.40%	-	Yes	Source
Qwen	Qwen 3.5 2B	02 Mar 2026	46.40%	-	Yes	Source
Qwen	Qwen 3.5 4B	02 Mar 2026	54.30%	-	Yes	Source
Qwen	Qwen 3.5 9B	02 Mar 2026	55.90%	-	Yes	Source
Qwen	Qwen 3.5 35B A3B	24 Feb 2026	57.10%	-	Yes	Source
Qwen	Qwen 3.6 Plus	01 Apr 2026	57.90%	-	Yes	Source
Qwen	Qwen 3.5 27B	24 Feb 2026	58.10%	-	Yes	Source
Qwen	Qwen 3.5 Flash	23 Feb 2026	58.10%	inferred family alias from qwen3.5-27b (score=0.4147; benches=81)	Yes	Source
Qwen	Qwen 3.5 122B A10B	24 Feb 2026	58.60%	-	Yes	Source
Qwen	Qwen 3.5 397B A17B	16 Feb 2026	59.10%	-	Yes	Source