Benchmark profile

NOVA-63

A broad multilingual benchmark row from Qwen's launch comparisons intended to measure cross-lingual capability beyond a single language family.

Data verified July 23, 2026

Benchmark score on NOVA-63 — July 23, 2026

BenchLM mirrors the published score view for NOVA-63. Qwen3.5 397B leads the public snapshot at 59.1% , followed by Qwen3.7 Max (59.0%) and Qwen3.7 Plus (58.8%). BenchLM does not use these results to rank models overall.

1Open

Qwen3.5 397B

Alibaba

qwen3-5-397b

59.1%

Overall 57.01Context 128K

2Closed

Qwen3.7 Max

Alibaba

qwen3-7-max

59.0%

Overall 72.84Context 1M

3Closed

Qwen3.7 Plus

Alibaba

qwen3-7-plus

58.8%

Overall 67.22Context 1M

7 modelsMultilingualCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (7 models)

Score

Qwen3.5 397BAlibaba · Open weight

59.1%

Qwen3.7 MaxAlibaba · Closed

59.0%

Qwen3.7 PlusAlibaba · Closed

58.8%

Qwen3.6 PlusAlibaba · Closed

57.9%

Claude Opus 4.5Anthropic · Closed

56.7%

Kimi K2.5Moonshot AI · Open weight

56.0%

GLM-5Z.AI · Open weight

55.1%

The published NOVA-63 snapshot places Qwen3.5 397B first at 59.1%. The third row is 0.3 points behind. The broader top-10 range is 4.0 points, so many of the published results sit in a relatively narrow band.

7 models have been evaluated on NOVA-63. The benchmark falls in the Multilingual category. This category carries a 7% weight in BenchLM.ai's overall scoring system. NOVA-63 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About NOVA-63

Year

2026

Tasks

Broad multilingual evaluation

Format

Cross-lingual benchmark

Difficulty

Broad multilingual capability

NOVA-63 appears in multilingual comparison tables as a harder broad-language benchmark than standard translated math. BenchLM tracks it as a display-only multilingual capability signal until a cleaner public benchmark specification is available.

Qwen3.6 launch benchmarks

BenchLM freshness & provenance

Version

NOVA-63 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does NOVA-63 measure?

A broad multilingual benchmark row from Qwen's launch comparisons intended to measure cross-lingual capability beyond a single language family.

Which model scores highest on NOVA-63?

Qwen3.5 397B by Alibaba currently leads with a score of 59.1% on NOVA-63.

How many models are evaluated on NOVA-63?

7 AI models have been evaluated on NOVA-63 on BenchLM.

Compare Top Models on NOVA-63

Qwen3.5 397B vs Qwen3.7 Max Qwen3.7 Max vs Qwen3.7 Plus Qwen3.7 Plus vs Qwen3.6 Plus Qwen3.6 Plus vs Claude Opus 4.5

Last updated: July 23, 2026 · BenchLM version NOVA-63 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.