Compare / Qwen3-Coder-480B-A35B vs DeepSeek-V4-Pro (0423)

Qwen3-Coder-480B-A35B vs DeepSeek-V4-Pro (0423)

Which is cheaper, which is more capable, and which does better at each kind of work, from 20 results on 3 sources that measured both models.

AlibabaQwen3-Coder-480B-A35B Released 31 Jul 2025 · $0.35 in · $1.50 out
DeepSeekDeepSeek-V4-Pro (0423) Released 24 Apr 2026 · $1.42 in · $2.83 out
Qwen3-Coder-480B-A35B wins 1DeepSeek-V4-Pro (0423) wins 19

Of the 20 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-Coder-480B-A35B 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 11.9). Pick Qwen3-Coder-480B-A35B if cost matters more: it costs 2.8 times less per token.

  • Qwen3-Coder-480B-A35B is cheaper: $0.64 against $1.77 per million tokens, 2.8 times less.
  • DeepSeek-V4-Pro (0423) scores higher on the Artificial Analysis Intelligence Index: 30.4 against 11.9.
  • DeepSeek-V4-Pro (0423) is newer: released 24 Apr 2026, against 31 Jul 2025 for Qwen3-Coder-480B-A35B.
  • 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

11.9
Intelligence Index
30.4
$0.64
Price per million tokens, blendedlower is better
$1.77
262,144
Context window, tokens
1,048,576

Every fact side by side

Qwen3-Coder-480B-A35BDeepSeek-V4-Pro (0423)
Price per million tokens$0.35 in · $1.50 out$1.42 in · $2.83 out
Blended (3 in : 1 out)$0.64$1.77
Cheapest host, blended$0.47 (DeepInfra, FP4)$1.19 (StreamLake, FP8)
Intelligence Index11.930.4
Spring Prompt overall–33
Output speed, tokens a second––
Context window262,144 tokens1,048,576 tokens
Released31 Jul 202524 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 162 of 164 86 of 164
Reasoning and knowledgeHard questions across science, maths and general knowledge 152 of 198 45 of 198
WritingWhat people prefer in blind comparisons, and judged writing quality 121 of 188 30 of 188
Sticking to the factsSummarising without inventing things, and factual answers 132 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-Coder-480B-A35BDeepSeek-V4-Pro (0423)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 156 · 53 of 387 measured 1,387 1,458
Overall · Text factualityArena rating, higher is better 135 · 49 of 163 measured 1,401 1,455
Business, management and finance · TextArena rating, higher is better 148 · 52 of 380 measured 1,391 1,460
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 154 · 49 of 243 measured 11.9 30.4max reasoning
GPQA Diamond% of questions, higher is better 178 · 37 of 231 measured 61.8% 90.5%high reasoning
Humanity's Last Exam% of questions, higher is better 202 · 51 of 242 measured 4.5% 37.5%max reasoning
OpenHands Index reported by OpenHands Index · 3 results
Average% resolved, higher is better 33 · 29 of 34 measured 30.9%openhands 40.7%openhands
Front end (SWE-Bench Multimodal)% resolved, higher is better 29 · 11 of 34 measured 23.5%openhands 36.8%openhands
Greenfield (Commit0)% resolved, higher is better 34 · 25 of 34 measured 0.0%openhands 12.5%openhands
Show all 20 results (11 more)
MeasureQwen3-Coder-480B-A35BDeepSeek-V4-Pro (0423)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 141 · 39 of 385 measured 1,363 1,446
Expert prompts · TextArena rating, higher is better 174 · 64 of 338 measured 1,379 1,480
Instruction following · TextArena rating, higher is better 144 · 52 of 387 measured 1,384 1,452
Writing, literature and language · TextArena rating, higher is better 150 · 44 of 386 measured 1,366 1,451
Artificial Analysis reported by Artificial Analysis · 4 results
IFBench% of instructions, higher is better 133 · 15 of 195 measured 40.5% 76.5%max reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 161 · 79 of 233 measured 45.7% 74.7%max reasoning
Terminal-Bench Hard% of tasks, higher is better 94 · 18 of 190 measured 18.9% 46.2%max reasoning
τ²-bench telecom% of tasks, higher is better 110 · 11 of 193 measured 43.6% 96.2%max reasoning
OpenHands Index reported by OpenHands Index · 3 results
Information gathering (GAIA)% resolved, higher is better 29 · 33 of 34 measured 33.9%openhands 12.7%openhands
Issue resolution (SWE-Bench)% resolved, higher is better 30 · 22 of 34 measured 62.4%openhands 73.2%openhands
Testing (SWT-Bench)% resolved, higher is better 32 · 18 of 34 measured 34.9%openhands 68.1%openhands

Quick answers

Is Qwen3-Coder-480B-A35B better than DeepSeek-V4-Pro (0423)?

Pick DeepSeek-V4-Pro (0423) if quality matters most: it scores higher (Intelligence Index 30.4 against 11.9). Pick Qwen3-Coder-480B-A35B if cost matters more: it costs 2.8 times less per token.

Which is cheaper, Qwen3-Coder-480B-A35B or DeepSeek-V4-Pro (0423)?

Qwen3-Coder-480B-A35B is cheaper: $0.64 against $1.77 per million tokens, 2.8 times less.

Which is better for agents and tool use, Qwen3-Coder-480B-A35B 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 162 for Qwen3-Coder-480B-A35B.

Which is better for reasoning and knowledge, Qwen3-Coder-480B-A35B 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 152 for Qwen3-Coder-480B-A35B.

Which is better for writing, Qwen3-Coder-480B-A35B 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 121 for Qwen3-Coder-480B-A35B.

Which is better for sticking to the facts, Qwen3-Coder-480B-A35B 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 132 for Qwen3-Coder-480B-A35B.

Which has the bigger context window, Qwen3-Coder-480B-A35B or DeepSeek-V4-Pro (0423)?

DeepSeek-V4-Pro (0423): 1,048,576 tokens, against 262,144 for Qwen3-Coder-480B-A35B.

Run Qwen3-Coder-480B-A35B 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