Compare / Qwen3.5-35B-A3B vs DeepSeek-R1
Qwen3.5-35B-A3B vs DeepSeek-R1
Which is cheaper, which is more capable, and which does better at each kind of work, from 21 results on 4 sources that measured both models.
Of the 21 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 9 October 2026 (catalogue release 2026-10-09-dd620e778ac5). See also Alibaba vs DeepSeek, every model from both labs.
Qwen3.5-35B-A3B or DeepSeek-R1? The short answer
Pick Qwen3.5-35B-A3B: it scores higher (Intelligence Index 19.3 against 11.4) and costs less.
- Qwen3.5-35B-A3B is cheaper: $0.45 against $1.15 per million tokens, 2.6 times less.
- Qwen3.5-35B-A3B scores higher on the Artificial Analysis Intelligence Index: 19.3 against 11.4.
- Qwen3.5-35B-A3B is newer: released 24 Feb 2026, against 20 Jan 2025 for DeepSeek-R1.
- On third-party benchmarks, on the results both models have: Qwen3.5-35B-A3B does better for reasoning and knowledge and sticking to the facts; DeepSeek-R1 for writing.
Head to head
Every fact side by side
| Qwen3.5-35B-A3B | DeepSeek-R1 | |
|---|---|---|
| Price per million tokens | $0.16 in · $1.30 out | $0.70 in · $2.50 out |
| Blended (3 in : 1 out) | $0.45 | $1.15 |
| Cheapest host, blended | $0.25 (Darkbloom, FP4) | – |
| Intelligence Index | 19.3 | 11.4 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 262,144 tokens | 64,000 tokens |
| Released | 24 Feb 2026 (newer) | 20 Jan 2025 |
| 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 | DeepSeek-R1 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 147 · 141 of 387 measured | 1,394 | 1,398 |
| Business, management and finance · TextArena rating, higher is better 139 · 151 of 380 measured | 1,403 | 1,388 |
| Creative writing · TextArena rating, higher is better 163 · 125 of 385 measured | 1,342 | 1,374 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 108 · 158 of 243 measured | 19.3 | 11.4 |
| GPQA Diamond% of questions, higher is better 84 · 154 of 231 measured | 84.5% | 70.8% |
| Humanity's Last Exam% of questions, higher is better 106 · 162 of 242 measured | 21.0% | 8.5% |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 97 · 74 of 230 measured | 42.6think-prefill reasoning | 51.8 |
| Requested-length error · UGI% off the requested word count, lower is better 83 · 91 of 230 measured | 17.0%no reasoning | 18.0% |
| Style adherence · UGIscore from 0 to 1, higher is better 151 · 203 of 230 measured | 0.33no reasoning | 0.30 |
| Vectara Hallucination Leaderboard reported by Vectara Hallucination Leaderboard · 2 results | ||
| Hallucination rate · Vectara% of summaries, lower is better 62 · 73 of 104 measured | 10.5% | 11.3% |
| Answer rate · Vectara% of documents, higher is better 31 · 84 of 104 measured | 99.8% | 97.0% |
Show all 21 results (10 more)
| Measure | Qwen3.5-35B-A3B | DeepSeek-R1 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Expert prompts · TextArena rating, higher is better 134 · 151 of 338 measured | 1,419 | 1,402 |
| Instruction following · TextArena rating, higher is better 140 · 128 of 387 measured | 1,386 | 1,397 |
| Writing, literature and language · TextArena rating, higher is better 155 · 130 of 386 measured | 1,363 | 1,382 |
| Artificial Analysis reported by Artificial Analysis · 7 results | ||
| Terminal-Bench 2.1% of tasks, higher is better 72 · 92 of 130 measured | 40.8%no reasoning | 19.1% |
| τ-bench banking% of tasks, higher is better 107 · 94 of 121 measured | 4.9%no reasoning | 6.4% |
| Artificial Analysis Coding Indexindex score, higher is better 79 · 92 of 131 measured | 37.0no reasoning | 24.6 |
| IFBench% of instructions, higher is better 39 · 141 of 195 measured | 72.5% | 39.0% |
| Long-context reasoning (AA-LCR)% of questions, higher is better 99 · 140 of 233 measured | 72.0% | 57.7% |
| Terminal-Bench Hard% of tasks, higher is better 74 · 147 of 190 measured | 26.5% | 6.1% |
| τ²-bench telecom% of tasks, higher is better 45 · 182 of 193 measured | 89.2% | 11.4% |
Compare them with other models
Quick answers
Is Qwen3.5-35B-A3B better than DeepSeek-R1?
Pick Qwen3.5-35B-A3B: it scores higher (Intelligence Index 19.3 against 11.4) and costs less.
Which is cheaper, Qwen3.5-35B-A3B or DeepSeek-R1?
Qwen3.5-35B-A3B is cheaper: $0.45 against $1.15 per million tokens, 2.6 times less.
Which is better for agents and tool use, Qwen3.5-35B-A3B or DeepSeek-R1?
Qwen3.5-35B-A3B ranks 116 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 126 for DeepSeek-R1.
Which is better for reasoning and knowledge, Qwen3.5-35B-A3B or DeepSeek-R1?
Qwen3.5-35B-A3B ranks 92 of 198 models on sale for hard questions across science, maths and general knowledge, against 136 for DeepSeek-R1.
Which is better for writing, Qwen3.5-35B-A3B or DeepSeek-R1?
DeepSeek-R1 ranks 91 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 108 for Qwen3.5-35B-A3B.
Which is better for sticking to the facts, Qwen3.5-35B-A3B or DeepSeek-R1?
DeepSeek-R1 ranks 110 of 152 models on sale for summarising without inventing things, and factual answers, against 112 for Qwen3.5-35B-A3B.
Which has the bigger context window, Qwen3.5-35B-A3B or DeepSeek-R1?
Qwen3.5-35B-A3B: 262,144 tokens, against 64,000 for DeepSeek-R1.
Run Qwen3.5-35B-A3B and DeepSeek-R1 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.