Skip to main content

Qwen3.5 35B-A3B vs Qwen3.6 35B-A3B

SpecQwen3.5 35B-A3BQwen3.6 35B-A3B
Respan Index18.4 (#144)26.0 (#107)
Blended price per 1M$0.158$0.158
Context window262K262K
Input / output per 1M$0.057 / $0.459$0.07 / $0.42
Max output--
Inputtext, visiontext, vision
Released--

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 35B-A3BQwen3.6 35B-A3B
Coding0.9 Qwen3.5 35B-A3B3.7 Qwen3.6 35B-A3B
Agents15.5* Qwen3.5 35B-A3B30.0* Qwen3.6 35B-A3B
Reasoning23.4 Qwen3.5 35B-A3B32.8 Qwen3.6 35B-A3B
Knowledge & language13.9* Qwen3.5 35B-A3B21.1 Qwen3.6 35B-A3B
Human preference47.1 Qwen3.5 35B-A3B48.3* Qwen3.6 35B-A3B

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

Benchmarks both report

Qwen3.6 35B-A3B leads on 4 of the 4 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkQwen3.5 35B-A3BQwen3.6 35B-A3B
Chess Puzzles (Epoch AI)10%26%
GPQA Diamond83.5%86%
OTIS Mock AIME 2024-2025 (Epoch AI)70%86.7%
SWE-rebench 2026-05-15 to 2026-07-01 (Nebius)17.1%24.7%

FAQ

Is Qwen3.5 35B-A3B better than Qwen3.6 35B-A3B?

Qwen3.6 35B-A3B scores 26.0 on the Respan Index (#107), ahead of Qwen3.5 35B-A3B at 18.4 (#144). Qwen3.6 35B-A3B leads on 4 of the 4 benchmarks both report.

Which is cheaper, Qwen3.5 35B-A3B or Qwen3.6 35B-A3B?

Qwen3.5 35B-A3B lists at $0.057 input and $0.459 output per 1M tokens; Qwen3.6 35B-A3B at $0.07 and $0.42. Both cost about the same per token at list price.

Which has the larger context window?

Both accept 262K tokens of context.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.