Compare / Qwen3.5-35B-A3B vs DeepSeek-V4-Pro (0423)

Qwen3.5-35B-A3B vs DeepSeek-V4-Pro (0423)

Which is cheaper, which is more capable, and which does better at each kind of work, from 22 results on 4 sources that measured both models.

AlibabaQwen3.5-35B-A3B Released 24 Feb 2026 · $0.16 in · $1.30 out
DeepSeekDeepSeek-V4-Pro (0423) Released 24 Apr 2026 · $1.42 in · $2.83 out
Qwen3.5-35B-A3B wins 2DeepSeek-V4-Pro (0423) wins 20

Of the 22 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-V4-Pro (0423)? The short answer

Pick DeepSeek-V4-Pro (0423) if quality matters most: it scores higher (Intelligence Index 30.4 against 19.3). Pick Qwen3.5-35B-A3B if cost matters more: it costs 4.0 times less per token.

  • Qwen3.5-35B-A3B is cheaper: $0.45 against $1.77 per million tokens, 4.0 times less.
  • DeepSeek-V4-Pro (0423) scores higher on the Artificial Analysis Intelligence Index: 30.4 against 19.3.
  • DeepSeek-V4-Pro (0423) is newer: released 24 Apr 2026, against 24 Feb 2026 for Qwen3.5-35B-A3B.
  • On third-party benchmarks, on the results both models have: DeepSeek-V4-Pro (0423) does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.

Head to head

19.3
Intelligence Index
30.4
$0.45
Price per million tokens, blendedlower is better
$1.77
262,144
Context window, tokens
1,048,576

Every fact side by side

Qwen3.5-35B-A3BDeepSeek-V4-Pro (0423)
Price per million tokens$0.16 in · $1.30 out$1.42 in · $2.83 out
Blended (3 in : 1 out)$0.45$1.77
Cheapest host, blended$0.25 (Darkbloom, FP4)$1.19 (StreamLake, FP8)
Intelligence Index19.330.4
Spring Prompt overall–33
Output speed, tokens a second––
Context window262,144 tokens1,048,576 tokens
Released24 Feb 202624 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.

Decks from an analysisTurning a finished analysis into a deck you could present as it is not measured 18 of 19
Marketing planningPlanning a year of ad spend without overspending not measured 13 of 19
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 116 of 164 86 of 164
Reasoning and knowledgeHard questions across science, maths and general knowledge 92 of 198 45 of 198
WritingWhat people prefer in blind comparisons, and judged writing quality 108 of 188 30 of 188
Sticking to the factsSummarising without inventing things, and factual answers 112 of 152 57 of 152
Speed under pressureGood decisions against a real clock (fast chess) not measured 24 of 24

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-A3BDeepSeek-V4-Pro (0423)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 147 · 53 of 387 measured 1,394 1,458
Overall · Text factualityArena rating, higher is better 129 · 49 of 163 measured 1,407 1,455
Business, management and finance · TextArena rating, higher is better 139 · 52 of 380 measured 1,403 1,460
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 108 · 49 of 243 measured 19.3 30.4max reasoning
GPQA Diamond% of questions, higher is better 84 · 37 of 231 measured 84.5% 90.5%high reasoning
Humanity's Last Exam% of questions, higher is better 106 · 51 of 242 measured 21.0% 37.5%max reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 97 · 15 of 230 measured 42.6think-prefill reasoning 68.4thinking reasoning
Requested-length error · UGI% off the requested word count, lower is better 83 · 177 of 230 measured 17.0%no reasoning 34.0%thinking reasoning
Style adherence · UGIscore from 0 to 1, higher is better 151 · 76 of 230 measured 0.33no reasoning 0.36thinking reasoning
Vectara Hallucination Leaderboard reported by Vectara Hallucination Leaderboard · 2 results
Hallucination rate · Vectara% of summaries, lower is better 62 · 44 of 104 measured 10.5% 8.6%
Answer rate · Vectara% of documents, higher is better 31 · 83 of 104 measured 99.8% 97.2%
Show all 22 results (11 more)
MeasureQwen3.5-35B-A3BDeepSeek-V4-Pro (0423)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 163 · 39 of 385 measured 1,342 1,446
Expert prompts · TextArena rating, higher is better 134 · 64 of 338 measured 1,419 1,480
Instruction following · TextArena rating, higher is better 140 · 52 of 387 measured 1,386 1,452
Writing, literature and language · TextArena rating, higher is better 155 · 44 of 386 measured 1,363 1,451
Artificial Analysis reported by Artificial Analysis · 7 results
Terminal-Bench 2.1% of tasks, higher is better 72 · 41 of 130 measured 40.8%no reasoning 64.8%high reasoning
τ-bench banking% of tasks, higher is better 107 · 35 of 121 measured 4.9%no reasoning 30.1%max reasoning
Artificial Analysis Coding Indexindex score, higher is better 79 · 40 of 131 measured 37.0no reasoning 59.4max reasoning
IFBench% of instructions, higher is better 39 · 15 of 195 measured 72.5% 76.5%max reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 99 · 79 of 233 measured 72.0% 74.7%max reasoning
Terminal-Bench Hard% of tasks, higher is better 74 · 18 of 190 measured 26.5% 46.2%max reasoning
τ²-bench telecom% of tasks, higher is better 45 · 11 of 193 measured 89.2% 96.2%max reasoning

Quick answers

Is Qwen3.5-35B-A3B better than DeepSeek-V4-Pro (0423)?

Pick DeepSeek-V4-Pro (0423) if quality matters most: it scores higher (Intelligence Index 30.4 against 19.3). Pick Qwen3.5-35B-A3B if cost matters more: it costs 4.0 times less per token.

Which is cheaper, Qwen3.5-35B-A3B or DeepSeek-V4-Pro (0423)?

Qwen3.5-35B-A3B is cheaper: $0.45 against $1.77 per million tokens, 4.0 times less.

Which is better for agents and tool use, Qwen3.5-35B-A3B or DeepSeek-V4-Pro (0423)?

DeepSeek-V4-Pro (0423) ranks 86 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 116 for Qwen3.5-35B-A3B.

Which is better for reasoning and knowledge, Qwen3.5-35B-A3B or DeepSeek-V4-Pro (0423)?

DeepSeek-V4-Pro (0423) ranks 45 of 198 models on sale for hard questions across science, maths and general knowledge, against 92 for Qwen3.5-35B-A3B.

Which is better for writing, Qwen3.5-35B-A3B or DeepSeek-V4-Pro (0423)?

DeepSeek-V4-Pro (0423) ranks 30 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-V4-Pro (0423)?

DeepSeek-V4-Pro (0423) ranks 57 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-V4-Pro (0423)?

DeepSeek-V4-Pro (0423): 1,048,576 tokens, against 262,144 for Qwen3.5-35B-A3B.

Run Qwen3.5-35B-A3B and DeepSeek-V4-Pro (0423) on your own prompt

Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.

Try the playgroundTalk to us