Benchmark

NOVA-63

NOVA-63 is a multilingual evaluation benchmark covering 63 languages, designed to assess LLM performance across diverse linguistic contexts and tasks.

Modality
text
Categories
general
Openness
unknown
Source
llm_stats
Reported scores
11

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Qwen3.5-0.8BQwen0.4242026-03-02evidence
Qwen3.5-122B-A10BQwen0.5862026-02-24evidence
Qwen3.5-27BQwen0.5812026-02-24evidence
Qwen3.5-2BQwen0.4642026-03-02evidence
Qwen3.5-35B-A3BQwen0.5712026-02-24evidence
Qwen3.5-397B-A17BQwen0.5912026-02-16evidence
Qwen3.5-4BQwen0.5432026-03-02evidence
Qwen3.5-9BQwen0.5592026-03-02evidence
Qwen3.6 PlusQwen0.5792026-04-02evidence
Qwen3.7 MaxQwen0.592026-05-19evidence
Qwen3.7-PlusQwen0.5882026-05-31evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.