Skip to main content

Qwen3.5 397B-A17B vs Qwen3.6-Max-Preview

SpecQwen3.5 397B-A17BQwen3.6-Max-Preview
Respan Index29.5 (#93)40.5 (#66)
Blended price per 1M$0.387-
Context window262K256K
Input / output per 1M$0.172 / $1.03-
Max output--
Inputtext, visiontext
Released2026-02-152026-04-18

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryQwen3.5 397B-A17BQwen3.6-Max-Preview
Coding11.2 Qwen3.5 397B-A17B19.2 Qwen3.6-Max-Preview
Agents34.3 Qwen3.5 397B-A17B54.0 Qwen3.6-Max-Preview
Reasoning30.8 Qwen3.5 397B-A17B36.1 Qwen3.6-Max-Preview
Knowledge & language27.6 Qwen3.5 397B-A17B51.9 Qwen3.6-Max-Preview
Human preference51.1 Qwen3.5 397B-A17B53.4 Qwen3.6-Max-Preview

How the Respan Index works

Benchmarks both report

Qwen3.6-Max-Preview leads on 5 of the 6 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkQwen3.5 397B-A17BQwen3.6-Max-Preview
LMArena Elo14411460
LMArena WebDev (LMArena)14001482
Chess Puzzles (Epoch AI)13%20%
GPQA Diamond88.4%87.4%
Mystery Game Puzzles (Epoch AI)18%19%
OTIS Mock AIME 2024-2025 (Epoch AI)88.9%91.1%

FAQ

Is Qwen3.5 397B-A17B better than Qwen3.6-Max-Preview?

Qwen3.6-Max-Preview scores 40.5 on the Respan Index (#66), ahead of Qwen3.5 397B-A17B at 29.5 (#93). Qwen3.6-Max-Preview leads on 5 of the 6 benchmarks both report.

Which has the larger context window?

Qwen3.5 397B-A17B accepts 262K tokens and Qwen3.6-Max-Preview 256K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.