Navigation

Qwen's experimental open-weight multimodal MoE preview of the Qwen4 architecture, with 125B total parameters, 6B activated parameters, 51B n-gram embeddings and native 262,144-token context.

#21· 65.9 · Rank #21 · Confidence D

Loading Qwen3.8-Flash-Next profile

Loading table

Loading Lumina Bench

Lumina Bench

Independent Score rankings from hard benchmarks — speed and price stay decision context, not rank inputs.

Product

Leaderboard
Compare
Models
Benchmarks

Research

How rankings work
Data
Changelog

Company

News
Contact
Advertise

Lumina Bench
Models
Qwen3.8-Flash-Next

Alibaba Cloud · preview

Qwen3.8-Flash-Next

Qwen's experimental open-weight multimodal MoE preview of the Qwen4 architecture, with 125B total parameters, 6B activated parameters, 51B n-gram embeddings and native 262,144-token context.

#21· 65.9 · Rank #21 · Confidence D

Loading Qwen3.8-Flash-Next profile