gpt.college

Alibaba Cloud · Qwen3.8 · Reviewed 2026-10-02

Qwen3.8-Flash-Next

Qwen's open-weight Flash-Next checkpoint with a vision encoder; distinct from the floating Flash API.

All models
Overall · 0–100—
Status
active
Released
—
Context
262,144 tokens
Parameters
125B total · 6B active
Inputs
Text · Image
Type
multimodal
Max output
— tokens
API model ID
—
Reasoning
—
Knowledge cutoff
—
Training cutoff
—
Weights / license
Available · License undisclosed
Price / 1M tokens
—
Cached input
—
Source-backed model profile
CodingReasoningResearchMultimodalAgentic

Independent benchmark scores

Raw benchmark results

Source-backed rows with the original evaluation context preserved.

1 results
BenchmarkScoreSourceEvaluation notes
Artificial Analysis Intelligence Index v4.3.2Checked 2026-10-02 40 Artificial Analysis Artificial Analysis Intelligence Index v4.3.2; configuration=Flash-Next open-weight checkpoint. Rounded public score; checked date is not the evaluation execution date.

Strengths

  • Source-backed model profile

Limitations

  • Additional n-gram embedding and MTP parameters are listed separately in the model card
  • Native context is 262,144 tokens; extension settings are separate

Model evidence · official · Checked 2026-09-04

Qwen3.8-Flash-Next model card

Official Qwen open-weight model card containing architecture, parameter breakdown, context extension, sampling guidance, and benchmark tables. Qwen documents Qwen3.8-Flash as the production version based on this preview.

Task lenses preserve raw scores. Radar axes use score / current leader × 100; overall is the equal-weight average of all five indices. Missing evidence is not a zero or a low rank.