Skip to content
Leaders Board.
Models/AlibabaOpen weights

Qwen3.5 397B A17B

Ranked on the boards below.
-
Overall rank
-
Podium score
0
Board wins
Feb 13, 2026
Released
·Chat·Reasoning·Coding·Vision

Chat

Which model people prefer in blind head-to-head conversations.

67
Text Arena
1,442 · of 100
as “qwen3.5-397b-a17b”

Reasoning

Hard questions with checkable answers: science, math, puzzles, expert exams.

7
MMLU-Pro
87.8% · of 100 · stale since 2026-03-11
as “Qwen3.5-397B-A17B”
51
GPQA Diamond
86.4% · of 100
as “qwen3.5-397b-a17b_none”
56
AA Intelligence
21.4 · of 100
as “Qwen3.5 397B A17B (Non-reasoning)”
66
Epoch ECI
146.6 · of 100
as “Qwen3.5 397B-A17B”

Coding

Fixing real repositories, building web apps, editing code.

65
WebDev Arena
1,399 · of 100
as “qwen3.5-397b-a17b”

Vision

Understanding images, charts and documents.

40
Vision Arena
1,248 · of 100
as “qwen3.5-397b-a17b”

More from Alibaba

Qwen3.8-Flash-NextQwen3.8 2.4T A95BQwen3.8 Max (0902)Qwen Audio 3.0 TTS PlusQwen3.8 27BQwen 3.8 27BQwen 3.8 MaxQwen3.7 Flash

Scores as published by each board on the capture date. Model names and logos belong to their owners; logos via logo.dev.

Weekly: the AI leaderboards with a new #1, Saturday mornings.