Alibaba
Qwen3.8 Max
2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows
alibaba/qwen3.8-max
Context
1M
Output
131.1K
Released
2026-08-03
Knowledge cutoff
—
Types
Reasoning
Tool use
Structured output
Attachments
Open weights
Provider pricing
- Price
- $2.00 / $6.00
- Context
- 1M
- Status
- Stable
- Price
- $2.00 / $6.00
- Context
- 983.6K
- Status
- Stable
- Price
- $2.00 / $6.00
- Context
- 262.1K
- Status
- Stable
- Price
- $2.60 / $7.80
- Context
- 1M
- Status
- Stable
Benchmarks
Terminal-Bench
86.6 · avg@10
SWE-Bench Pro
67.7 · resolved
DeepSWE
56.6 · score
NL2Repo
55.9 · score
FrontierSWE
73.5 · dominance score
MLS-Bench-Lite
41 · score
PaperBench
93 · score
AndroidBench
75.1 · avg@3
QwenSWEBench
80.7 · avg@3
QwenQoderBench
58.4 · avg@5
QwenReactBench
1724 · Elo
QwenSVGBench
1713 · Elo
CoWorkBench
74.8 · score
WorkSpaceBench
67.7 · score
JobBench
53.4 · score
SkillsBench
70.2 · avg@3
Agents' Last Exam
27 · pass@1
Agents' Last Exam
52.4 · score
AutomationBench
27.3 · pass@1
Toolathlon-Verified
72.5 · pass@1
WideSearch
81.9 · average item F1
Humanity's Last Exam
56.2 · score
Humanity's Last Exam
43.6 · score
GPQA Diamond
92.6 · score
IFBench
82.8 · score
$OneMillion-Bench
52.5 · expert score
HealthBench
60.2 · score
PLawBench
73.2 · score
PRBench
57.6 · score
PRBench
58.3 · score
MRCR
92.9 · score
LongBench
66.3 · score
From the same lab
Qwen 3.8 Max Prime
alibaba/qwen3.8-max-prime
Qwen3.8 Omni Flash
alibaba/qwen3.8-omni-flash
Qwen-Image-2.1
alibaba/qwen-image-2.1
Qwen3.8 Max 0902
alibaba/qwen3.8-max-0902
Qwen3.8 Flash Next
alibaba/qwen3.8-flash-next
Qwen3.8 Flash
alibaba/qwen3.8-flash
Qwen3.8 27B
alibaba/qwen3.8-27b
Qwen3.8 2.4T A95B
alibaba/qwen3.8-2.4t-a95b