Skip to main content

Qwen3.5 397B-A17B vs Qwen3.7-Plus

SpecQwen3.5 397B-A17BQwen3.7-Plus
Respan Index29.5 (#93)36.4 (#75)
Blended price per 1M$0.387$0.482
Context window262K1M
Input / output per 1M$0.172 / $1.03$0.276 / $1.1
Max output--
Inputtext, visiontext, vision
Released2026-02-152026-05-26

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-A17BQwen3.7-Plus
Coding11.2 Qwen3.5 397B-A17B15.1* Qwen3.7-Plus
Agents34.3 Qwen3.5 397B-A17B49.9 Qwen3.7-Plus
Reasoning30.8 Qwen3.5 397B-A17B34.8 Qwen3.7-Plus
Knowledge & language27.6 Qwen3.5 397B-A17B32.9* Qwen3.7-Plus
Human preference51.1 Qwen3.5 397B-A17B54.1 Qwen3.7-Plus

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

Qwen3.7-Plus leads on 6 of the 8 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkQwen3.5 397B-A17BQwen3.7-Plus
LMArena Elo14411455
LMArena Vision (LMArena)12461262
SAGE 1.1 (Vals AI)85.5%89.1%
Chess Puzzles (Epoch AI)13%24%
FrontierMath Tiers 1-3 v2 (Epoch AI)31.2%34.4%
GPQA Diamond88.4%87.9%
Mystery Game Puzzles (Epoch AI)18%17%
OTIS Mock AIME 2024-2025 (Epoch AI)88.9%93.3%

FAQ

Is Qwen3.5 397B-A17B better than Qwen3.7-Plus?

Qwen3.7-Plus scores 36.4 on the Respan Index (#75), ahead of Qwen3.5 397B-A17B at 29.5 (#93). Qwen3.7-Plus leads on 6 of the 8 benchmarks both report.

Which is cheaper, Qwen3.5 397B-A17B or Qwen3.7-Plus?

Qwen3.5 397B-A17B lists at $0.172 input and $1.03 output per 1M tokens; Qwen3.7-Plus at $0.276 and $1.1. Qwen3.5 397B-A17B is 1.2x cheaper per token at list price.

Which has the larger context window?

Qwen3.5 397B-A17B accepts 262K tokens and Qwen3.7-Plus 1M tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.