Knowledge · Benchmark profile
A broad multilingual benchmark row from Qwen's launch comparisons intended to measure cross-lingual capability beyond a single language family.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on NOVA-63
Qwen3.5 397B leads at 59.1%, followed by Qwen3.7-Max (59%) and Qwen3.7-Plus (58.8%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
7 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Qwen3.5 397B | #1 | Alibaba Cloud | 59.1% |
| Qwen3.7-Max | #2 | Alibaba Cloud | 59% |
| Qwen3.7-Plus | #3 | Alibaba Cloud | 58.8% |
| Qwen3.6 Plus | #4 | Alibaba Cloud | 57.9% |
| Claude Opus 4.5 | #5 | Anthropic | 56.7% |
| Kimi K2.5 | #6 | Moonshot AI | 56% |
| GLM-5 | #7 | Z.AI | 55.1% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Qwen3.5 397B qwen3.5-397b-a17b | Alibaba Cloud | open | Estimated reference | 59.1% |
| #2 | Qwen3.7-Max qwen3.7-max | Alibaba Cloud | — | Reference only | 59% |
| #3 | Qwen3.7-Plus qwen3.7-plus | Alibaba Cloud | — | Reference only | 58.8% |
| #4 | Qwen3.6 Plus qwen3-6-plus | Alibaba Cloud | closed | Reference only | 57.9% |
| #5 | Claude Opus 4.5 claude-opus-4-5 | Anthropic | closed | Reference only | 56.7% |
| #6 | Kimi K2.5 kimi-k2.5 | Moonshot AI | — | Reference only | 56% |
| #7 | GLM-5 glm-5 | Z.AI | open | Reference only | 55.1% |
The top of this snapshot is led by Qwen3.5 397B at 59.1%; third place is 0.30 points behind. The top-7 spread is 4.0 points.
About NOVA-63
A broad multilingual benchmark row from Qwen's launch comparisons intended to measure cross-lingual capability beyond a single language family. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
A broad multilingual benchmark row from Qwen's launch comparisons intended to measure cross-lingual capability beyond a single language family.
Qwen3.5 397B by Alibaba Cloud currently leads with 59.1%.
7 models in the LuminaBench cohort have a qualifying score on this benchmark.
No. This benchmark is display-only and does not enter the overall Lumina composite.
Related
2026 · 10 results · Reference
Artificial Analysis MMLU-Pro2026 · 4 results · Reference
Massive Multitask Language Understanding2020 · 8 results · Reference
Graduate-Level Google-Proof Q&A2023 · 70 results · Reference
SuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines2025 · 19 results · Reference
Massive Multitask Language Understanding Professional2024 · 42 results · Reference
