Compare / Qwen3.5-122B-A10B vs Mistral Medium 3.5

Qwen3.5-122B-A10B vs Mistral Medium 3.5

Which is cheaper, which is more capable, and which does better at each kind of work, from 24 results on 3 sources that measured both models.

AlibabaQwen3.5-122B-A10B Released 24 Feb 2026 · $0.26 in · $2.08 out
Mistral AIMistral Medium 3.5 Released 28 Apr 2026 · $1.50 in · $7.50 out
Qwen3.5-122B-A10B wins 96 too close to callMistral Medium 3.5 wins 9

Of the 24 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee). See also Alibaba vs Mistral AI, every model from both labs.

Qwen3.5-122B-A10B or Mistral Medium 3.5? The short answer

Pick Qwen3.5-122B-A10B: it scores higher (Intelligence Index 17.7 against 14.2) and costs less.

  • Qwen3.5-122B-A10B is cheaper: $0.72 against $3.00 per million tokens, 4.2 times less.
  • Qwen3.5-122B-A10B scores higher on the Artificial Analysis Intelligence Index: 17.7 against 14.2.
  • Mistral Medium 3.5 is newer: released 28 Apr 2026, against 24 Feb 2026 for Qwen3.5-122B-A10B.
  • On third-party benchmarks, on the results both models have: Qwen3.5-122B-A10B does better for reasoning and knowledge; Mistral Medium 3.5 for writing.

Head to head

17.7
Intelligence Index
14.2
$0.72
Price per million tokens, blendedlower is better
$3.00
144
Output speed, tokens a second
157
262,144
Context window, tokens
262,144

Every fact side by side

Qwen3.5-122B-A10BMistral Medium 3.5
Price per million tokens$0.26 in · $2.08 out$1.50 in · $7.50 out
Blended (3 in : 1 out)$0.72$3.00
Cheapest host, blended$0.72 (Alibaba)$3.00 (Mistral)
Cached input, per million–$0.15 cached input
Intelligence Index17.714.2
Spring Prompt overall–15
Output speed, tokens a second144157
Context window262,144 tokens262,144 tokens
Released24 Feb 202628 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 23 of 32
Decks from an analysisTurning a finished analysis into a deck you could present as it is not measured 31 of 32
User surveysPlanning a user survey and reading its results without being misled not measured 21 of 23
Marketing planningPlanning a year of ad spend without overspending not measured 32 of 32
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 101 of 159 100 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 92 of 187 123 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 98 of 169 85 of 169
Sticking to the factsSummarising without inventing things, and factual answers 103 of 139 98 of 139
Speed under pressureGood decisions against a real clock (fast chess) not measured 10 of 35

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.

MeasureQwen3.5-122B-A10BMistral Medium 3.5
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 117 · 99 of 387 measured 1,416 1,427
Overall · Text factualityArena rating, higher is better 103 · 97 of 163 measured 1,428 1,431
Business, management and finance · TextArena rating, higher is better 105 · 98 of 380 measured 1,422 1,430
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 120 · 139 of 249 measured 17.7no reasoning 14.2
GPQA Diamond% of questions, higher is better 76 · 140 of 232 measured 85.7% 74.8%
Humanity's Last Exam% of questions, higher is better 100 · 139 of 250 measured 25.2% 13.8%
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 112 · 86 of 230 measured 39.5no reasoning 45.5no reasoning
Requested-length error · UGI% off the requested word count, lower is better 33 · 91 of 230 measured 9.0%thinking reasoning 18.0%no reasoning
Style adherence · UGIscore from 0 to 1, higher is better 83 · 108 of 230 measured 0.36no reasoning 0.35no reasoning
Show all 24 results (15 more)
MeasureQwen3.5-122B-A10BMistral Medium 3.5
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 136 · 95 of 385 measured 1,366 1,400
Expert prompts · TextArena rating, higher is better 111 · 119 of 338 measured 1,442 1,435
Instruction following · TextArena rating, higher is better 115 · 92 of 387 measured 1,406 1,422
Writing, literature and language · TextArena rating, higher is better 125 · 100 of 386 measured 1,387 1,405
Artificial Analysis reported by Artificial Analysis · 11 results
Terminal-Bench 2.1% of tasks, higher is better 65 · 63 of 131 measured 47.6% 50.6%
Terminal-Bench 4.0% of tasks, higher is better 72 · 72 of 120 measured 0.0% 0.0%
τ-bench banking% of tasks, higher is better 58 · 60 of 121 measured 15.3% 15.1%
Artificial Analysis Coding Indexindex score, higher is better 64 · 61 of 130 measured 45.7 46.9
IFBench% of instructions, higher is better 22 · 59 of 195 measured 75.7% 68.8%
Long-context reasoning (AA-LCR)% of questions, higher is better 79 · 120 of 241 measured 76.3% 69.3%
Output speedtokens per second, higher is better 28 · 22 of 78 measured 144no reasoning 157
SciCode% of problems, higher is better 87 · 85 of 121 measured 39.7% 40.2%
Terminal-Bench Hard% of tasks, higher is better 65 · 57 of 190 measured 31.1% 33.3%
Time to first answer tokenseconds, lower is better 26 · 52 of 78 measured 0.99no reasoning 13.3
τ²-bench telecom% of tasks, higher is better 30 · 25 of 193 measured 93.6% 94.2%

Quick answers

Is Qwen3.5-122B-A10B better than Mistral Medium 3.5?

Pick Qwen3.5-122B-A10B: it scores higher (Intelligence Index 17.7 against 14.2) and costs less.

Which is cheaper, Qwen3.5-122B-A10B or Mistral Medium 3.5?

Qwen3.5-122B-A10B is cheaper: $0.72 against $3.00 per million tokens, 4.2 times less.

Which is faster, Qwen3.5-122B-A10B or Mistral Medium 3.5?

Mistral Medium 3.5 writes about 157 tokens a second on its usual API, against 144 for Qwen3.5-122B-A10B (Artificial Analysis).

Which is better for agents and tool use, Qwen3.5-122B-A10B or Mistral Medium 3.5?

Mistral Medium 3.5 ranks 100 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 101 for Qwen3.5-122B-A10B.

Which is better for reasoning and knowledge, Qwen3.5-122B-A10B or Mistral Medium 3.5?

Qwen3.5-122B-A10B ranks 92 of 187 models on sale for hard questions across science, maths and general knowledge, against 123 for Mistral Medium 3.5.

Which is better for writing, Qwen3.5-122B-A10B or Mistral Medium 3.5?

Mistral Medium 3.5 ranks 85 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 98 for Qwen3.5-122B-A10B.

Which is better for sticking to the facts, Qwen3.5-122B-A10B or Mistral Medium 3.5?

Mistral Medium 3.5 ranks 98 of 139 models on sale for summarising without inventing things, and factual answers, against 103 for Qwen3.5-122B-A10B.

Run Qwen3.5-122B-A10B and Mistral Medium 3.5 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.