Compare / Qwen3-235B-A22B-Thinking-2507 vs Mistral Medium 3.5

Qwen3-235B-A22B-Thinking-2507 vs Mistral Medium 3.5

Which is cheaper, which is more capable, and which does better at each kind of work, from 21 results on 3 sources that measured both models.

AlibabaQwen3-235B-A22B-Thinking-2507 Released 25 Jul 2025 · $0.30 in · $3.00 out
Mistral AIMistral Medium 3.5 Released 28 Apr 2026 · $1.50 in · $7.50 out
Qwen3-235B-A22B-Thinking-2507 wins 44 too close to callMistral Medium 3.5 wins 13

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 Mistral AI, every model from both labs.

Qwen3-235B-A22B-Thinking-2507 or Mistral Medium 3.5? The short answer

They score about the same, so pick Qwen3-235B-A22B-Thinking-2507: it costs 3.1 times less per token.

  • Qwen3-235B-A22B-Thinking-2507 is cheaper: $0.97 against $3.00 per million tokens, 3.1 times less.
  • Mistral Medium 3.5 scores higher on the Artificial Analysis Intelligence Index: 14.2 against 12.7.
  • Mistral Medium 3.5 is newer: released 28 Apr 2026, against 25 Jul 2025 for Qwen3-235B-A22B-Thinking-2507.
  • On third-party benchmarks, on the results both models have: Qwen3-235B-A22B-Thinking-2507 does better for reasoning and knowledge; Mistral Medium 3.5 for agents and tool use and writing.

Head to head

12.7
Intelligence Index
14.2
$0.97
Price per million tokens, blendedlower is better
$3.00
131,072
Context window, tokens
262,144

Every fact side by side

Qwen3-235B-A22B-Thinking-2507Mistral Medium 3.5
Price per million tokens$0.30 in · $3.00 out$1.50 in · $7.50 out
Blended (3 in : 1 out)$0.97$3.00
Cheapest host, blended$0.75 (Alibaba)$3.00 (Mistral)
Cached input, per million–$0.15 cached input
Intelligence Index12.714.2
Spring Prompt overall–18
Output speed, tokens a second–160
Context window131,072 tokens262,144 tokens
Released25 Jul 202528 Apr 2026 (newer)
WeightsOpenClosed
Developer based inChinaFrance

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.

Product listingsTurning a sparse product feed and photos into listings that can go live not measured 14 of 20
Decks from an analysisTurning a finished analysis into a deck you could present as it is not measured 16 of 19
User surveysPlanning a user survey and reading its results without being misled not measured 7 of 8
Marketing planningPlanning a year of ad spend without overspending not measured 19 of 19
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 138 of 164 93 of 164
Reasoning and knowledgeHard questions across science, maths and general knowledge 117 of 198 122 of 198
WritingWhat people prefer in blind comparisons, and judged writing quality 122 of 188 86 of 188
Sticking to the factsSummarising without inventing things, and factual answers 92 of 152 100 of 152
Speed under pressureGood decisions against a real clock (fast chess) not measured 9 of 23

From our research

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.

MeasureQwen3-235B-A22B-Thinking-2507Mistral Medium 3.5
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 139 · 99 of 387 measured 1,400 1,427
Business, management and finance · TextArena rating, higher is better 133 · 98 of 380 measured 1,404 1,430
Creative writing · TextArena rating, higher is better 133 · 95 of 385 measured 1,371 1,400
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 147 · 133 of 243 measured 12.7 14.2
GPQA Diamond% of questions, higher is better 114 · 139 of 231 measured 79.0% 74.8%
Humanity's Last Exam% of questions, higher is better 122 · 131 of 242 measured 15.9% 13.8%
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 139 · 86 of 230 measured 32.4 45.5no reasoning
Requested-length error · UGI% off the requested word count, lower is better 166 · 91 of 230 measured 30.0% 18.0%no reasoning
Style adherence · UGIscore from 0 to 1, higher is better 194 · 108 of 230 measured 0.31 0.35no reasoning
Show all 21 results (12 more)
MeasureQwen3-235B-A22B-Thinking-2507Mistral Medium 3.5
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 85 · 119 of 338 measured 1,466 1,435
Instruction following · TextArena rating, higher is better 142 · 92 of 387 measured 1,385 1,422
Writing, literature and language · TextArena rating, higher is better 139 · 100 of 386 measured 1,377 1,405
Artificial Analysis reported by Artificial Analysis · 9 results
Terminal-Bench 2.1% of tasks, higher is better 101 · 62 of 130 measured 12.0% 50.6%
Terminal-Bench 4.0% of tasks, higher is better 66 · 66 of 112 measured 0.0% 0.0%
τ-bench banking% of tasks, higher is better 87 · 60 of 121 measured 7.8% 15.1%
Artificial Analysis Coding Indexindex score, higher is better 98 · 62 of 131 measured 22.1 46.9
IFBench% of instructions, higher is better 101 · 59 of 195 measured 51.2% 68.8%
Long-context reasoning (AA-LCR)% of questions, higher is better 99 · 113 of 233 measured 72.0% 69.3%
SciCode% of problems, higher is better 74 · 77 of 113 measured 41.4% 40.2%
Terminal-Bench Hard% of tasks, higher is better 116 · 57 of 190 measured 13.6% 33.3%
τ²-bench telecom% of tasks, higher is better 101 · 25 of 193 measured 53.2% 94.2%

Quick answers

Is Qwen3-235B-A22B-Thinking-2507 better than Mistral Medium 3.5?

They score about the same, so pick Qwen3-235B-A22B-Thinking-2507: it costs 3.1 times less per token.

Which is cheaper, Qwen3-235B-A22B-Thinking-2507 or Mistral Medium 3.5?

Qwen3-235B-A22B-Thinking-2507 is cheaper: $0.97 against $3.00 per million tokens, 3.1 times less.

Which is better for agents and tool use, Qwen3-235B-A22B-Thinking-2507 or Mistral Medium 3.5?

Mistral Medium 3.5 ranks 93 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 138 for Qwen3-235B-A22B-Thinking-2507.

Which is better for reasoning and knowledge, Qwen3-235B-A22B-Thinking-2507 or Mistral Medium 3.5?

Qwen3-235B-A22B-Thinking-2507 ranks 117 of 198 models on sale for hard questions across science, maths and general knowledge, against 122 for Mistral Medium 3.5.

Which is better for writing, Qwen3-235B-A22B-Thinking-2507 or Mistral Medium 3.5?

Mistral Medium 3.5 ranks 86 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 122 for Qwen3-235B-A22B-Thinking-2507.

Which is better for sticking to the facts, Qwen3-235B-A22B-Thinking-2507 or Mistral Medium 3.5?

Qwen3-235B-A22B-Thinking-2507 ranks 92 of 152 models on sale for summarising without inventing things, and factual answers, against 100 for Mistral Medium 3.5.

Which has the bigger context window, Qwen3-235B-A22B-Thinking-2507 or Mistral Medium 3.5?

Mistral Medium 3.5: 262,144 tokens, against 131,072 for Qwen3-235B-A22B-Thinking-2507.

Run Qwen3-235B-A22B-Thinking-2507 and Mistral Medium 3.5 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