MMODELYST
Models/Qwen3 Max Thinking
MDL

Qwen3 Max Thinking

Alibaba

Verified against Artificial Analysis · Jul 13, 2026
Capability
84
percentile index
Price /M
$0 / $0
in / out
Context
262.1K
tokens
Avg score
57.1
7 benchmarks
AA Intelligence
31.7
index
Weights
Open
Released
Jan 26, 2026
About

Qwen3 Max Thinking is a open-weights model in the Qwen3 family from Alibaba. Benchmarked on 7 evals, averaging 57.1.

Benchmark scores · 7
avg 57.1 — higher is better
GPQA Diamond
86.1
τ²-bench
83.6
IFBench
70.7
AA Long-Context Reasoning
66
SciCode
43.1
Humanity's Last Exam
26.2
Terminal-Bench Hard
24.2
The research behind this model
all papers mentioning it →

Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.

Details
PublisherAlibaba
FamilyQwen3
Parameters
License
WeightsOpen
ReleasedJan 26, 2026
Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$0/M