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

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

Which is cheaper, which is more capable, and which does better at each kind of work, from 13 results on 2 sources that measured both models.

AlibabaQwen3.5-35B-A3B Released 24 Feb 2026 · $0.15 in · $1.00 out
AlibabaQwen3.6-35B-A3B Released 16 Apr 2026 · $0.10 in · $0.95 out
Qwen3.5-35B-A3B wins 5Qwen3.6-35B-A3B wins 8

Of the 13 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 19 November 2026 (catalogue release 2026-11-19-3608133e8331).

Qwen3.5-35B-A3B or Qwen3.6-35B-A3B? The short answer

Qwen3.6-35B-A3B is the newer version; they score about the same at about the same price.

  • They cost about the same: $0.36 and $0.31 per million tokens (three input to one output).
  • Qwen3.5-35B-A3B scores higher on the Artificial Analysis Intelligence Index: 19.3 against 18.2.
  • Qwen3.6-35B-A3B is newer: released 16 Apr 2026, against 24 Feb 2026 for Qwen3.5-35B-A3B.
  • On third-party benchmarks, on the results both models have: Qwen3.5-35B-A3B does better for reasoning and knowledge; Qwen3.6-35B-A3B for agents and tool use and writing.

Head to head

19.3
Intelligence Index
18.2
$0.36
Price per million tokens, blendedlower is better
$0.31
262,144
Context window, tokens
262,144

Every fact side by side

Qwen3.5-35B-A3BQwen3.6-35B-A3B
Price per million tokens$0.15 in · $1.00 out$0.10 in · $0.95 out
Blended (3 in : 1 out)$0.36$0.31
Cheapest host, blended$0.24 (Darkbloom, FP4)$0.037 (PrimeIntellect, FP8)
Intelligence Index19.318.2
Spring Prompt overall––
Output speed, tokens a second–135
Context window262,144 tokens262,144 tokens
Released24 Feb 202616 Apr 2026 (newer)
WeightsOpenOpen
Developer based inChinaChina

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 121 of 159 113 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 97 of 187 100 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 100 of 169 88 of 169
Sticking to the factsSummarising without inventing things, and factual answers 108 of 139 not measured

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureQwen3.5-35B-A3BQwen3.6-35B-A3B
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 114 · 118 of 249 measured 19.3 18.2
GPQA Diamond% of questions, higher is better 85 · 89 of 232 measured 84.5% 84.1%
Humanity's Last Exam% of questions, higher is better 114 · 109 of 250 measured 21.0% 22.2%
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 97 · 87 of 230 measured 42.6think-prefill reasoning 45.4think-prefill reasoning
Requested-length error · UGI% off the requested word count, lower is better 83 · 43 of 230 measured 17.0%no reasoning 10.0%no reasoning
Style adherence · UGIscore from 0 to 1, higher is better 151 · 174 of 230 measured 0.33no reasoning 0.32no reasoning
Show all 13 results (7 more)
MeasureQwen3.5-35B-A3BQwen3.6-35B-A3B
Artificial Analysis reported by Artificial Analysis · 7 results
Terminal-Bench 2.1% of tasks, higher is better 73 · 69 of 131 measured 40.8%no reasoning 44.9%
τ-bench banking% of tasks, higher is better 107 · 82 of 121 measured 4.9%no reasoning 9.3%
Artificial Analysis Coding Indexindex score, higher is better 78 · 71 of 130 measured 37.0no reasoning 41.9
IFBench% of instructions, higher is better 39 · 71 of 195 measured 72.5% 64.4%
Long-context reasoning (AA-LCR)% of questions, higher is better 105 · 108 of 241 measured 72.0% 71.7%
Terminal-Bench Hard% of tasks, higher is better 74 · 49 of 190 measured 26.5% 34.8%
τ²-bench telecom% of tasks, higher is better 45 · 20 of 193 measured 89.2% 95.3%

Quick answers

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

Qwen3.6-35B-A3B is the newer version; they score about the same at about the same price.

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

They cost about the same: $0.36 and $0.31 per million tokens (three input to one output).

Which is better for agents and tool use, Qwen3.5-35B-A3B or Qwen3.6-35B-A3B?

Qwen3.6-35B-A3B ranks 113 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 121 for Qwen3.5-35B-A3B.

Which is better for reasoning and knowledge, Qwen3.5-35B-A3B or Qwen3.6-35B-A3B?

Qwen3.5-35B-A3B ranks 97 of 187 models on sale for hard questions across science, maths and general knowledge, against 100 for Qwen3.6-35B-A3B.

Which is better for writing, Qwen3.5-35B-A3B or Qwen3.6-35B-A3B?

Qwen3.6-35B-A3B ranks 88 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 100 for Qwen3.5-35B-A3B.

Run Qwen3.5-35B-A3B and Qwen3.6-35B-A3B on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.