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.
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
Every fact side by side
| Qwen3.5-35B-A3B | Qwen3.6-35B-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 Index | 19.3 | 18.2 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | 135 |
| Context window | 262,144 tokens | 262,144 tokens |
| Released | 24 Feb 2026 | 16 Apr 2026 (newer) |
| Weights | Open | Open |
| Developer based in | China | China |
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.
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.
| Measure | Qwen3.5-35B-A3B | Qwen3.6-35B-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)
| Measure | Qwen3.5-35B-A3B | Qwen3.6-35B-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.