gpt.college

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

Qwen3.8-Max

Alibaba's Qwen3.8 flagship API model; the September snapshot has a separate record.

All models
Overall · 0–10062.9
Status
active
Released
2026-08-03
Context
1,000,000 tokens
Parameters
2.4T total · 95B active
Inputs
Text · Image · Video
Type
multimodal
Max output
131,072 tokens
API model ID
qwen3.8-max
Reasoning
—
Knowledge cutoff
—
Training cutoff
—
Weights / license
—
Price / 1M tokens
—
Cached input
—
Native visual input1M-token contextLong-horizon coding
CodingReasoningResearchMultimodalAgentic

Independent benchmark scores

Raw benchmark results

Source-backed rows with the original evaluation context preserved.

6 results
BenchmarkScoreSourceEvaluation notes
AutomationBench-AAChecked 2026-10-02 49% Artificial Analysis Artificial Analysis Intelligence Index v4.3.2; configuration=0803 release · reasoning enabled. Rounded public score; checked date is not the evaluation execution date.
AA GDP.pdfChecked 2026-10-02 20% Artificial Analysis Artificial Analysis Intelligence Index v4.3.2; configuration=0803 release · reasoning enabled. Rounded public score; checked date is not the evaluation execution date.
GDPval-AA v2.1Checked 2026-10-02 1608 Artificial Analysis Artificial Analysis Intelligence Index v4.3.2; configuration=0803 release · reasoning enabled. Rounded public score; checked date is not the evaluation execution date.
AA Humanity's Last ExamChecked 2026-10-02 43% Artificial Analysis Artificial Analysis Intelligence Index v4.3.2; configuration=0803 release · reasoning enabled. Rounded public score; checked date is not the evaluation execution date.
Artificial Analysis Intelligence Index v4.3.2Checked 2026-10-02 40 Artificial Analysis Artificial Analysis Intelligence Index v4.3.2; configuration=0803 release · reasoning enabled. Rounded public score; checked date is not the evaluation execution date.
AA Terminal-Bench 4.0Checked 2026-10-02 19% Artificial Analysis Artificial Analysis Intelligence Index v4.3.2; configuration=0803 release · reasoning enabled. Rounded public score; checked date is not the evaluation execution date.

Strengths

  • Native visual input
  • 1M-token context
  • Long-horizon coding

Limitations

  • Regional API pricing differs
  • Floating API aliases and dated snapshots may change independently

Model evidence · official · Checked 2026-10-02

Alibaba unveils Qwen3.8-Max

Official release or model documentation reviewed 2026-10-02; unconfirmed fields are left unset.

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.