Benchmark
NOVA-63 Benchmark
What is 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
- Evaluates
- general
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 11
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/nova-63?top_n=500
NOVA-63 results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen3.5-0.8B | Qwen | 0.424 | 2026-03-02 | evidence |
| Qwen3.5-122B-A10B | Qwen | 0.586 | 2026-02-24 | evidence |
| Qwen3.5-27B | Qwen | 0.581 | 2026-02-24 | evidence |
| Qwen3.5-2B | Qwen | 0.464 | 2026-03-02 | evidence |
| Qwen3.5-35B-A3B | Qwen | 0.571 | 2026-02-24 | evidence |
| Qwen3.5-397B-A17B | Qwen | 0.591 | 2026-02-16 | evidence |
| Qwen3.5-4B | Qwen | 0.543 | 2026-03-02 | evidence |
| Qwen3.5-9B | Qwen | 0.559 | 2026-03-02 | evidence |
| Qwen3.6 Plus | Qwen | 0.579 | 2026-04-02 | evidence |
| Qwen3.7 Max | Qwen | 0.59 | 2026-05-19 | evidence |
| Qwen3.7-Plus | Qwen | 0.588 | 2026-05-31 | evidence |
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.