Compare / Qwen3.5-122B-A10B vs Ministral 3 14B

Qwen3.5-122B-A10B vs Ministral 3 14B

Which is cheaper, which is more capable, and which does better at each kind of work, from 19 results on 3 sources that measured both models.

AlibabaQwen3.5-122B-A10B Released 24 Feb 2026 · $0.26 in · $2.08 out
Mistral AIMinistral 3 14B Released 2 Dec 2025 · $0.20 in · $0.20 out
Qwen3.5-122B-A10B wins 171 too close to callMinistral 3 14B wins 1

Of the 19 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.

Qwen3.5-122B-A10B or Ministral 3 14B? The short answer

Pick Qwen3.5-122B-A10B if quality matters most: it scores higher (Intelligence Index 17.7 against 6.0). Pick Ministral 3 14B if cost matters more: it costs 3.6 times less per token. Qwen3.5-122B-A10B is also faster.

  • Ministral 3 14B is cheaper: $0.20 against $0.72 per million tokens, 3.6 times less.
  • Qwen3.5-122B-A10B scores higher on the Artificial Analysis Intelligence Index: 17.7 against 6.0.
  • Qwen3.5-122B-A10B writes faster: 147 tokens a second against 81.
  • Qwen3.5-122B-A10B is newer: released 24 Feb 2026, against 2 Dec 2025 for Ministral 3 14B.
  • On third-party benchmarks, on the results both models have: Qwen3.5-122B-A10B does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.

Head to head

17.7
Intelligence Index
6.0
$0.72
Price per million tokens, blendedlower is better
$0.20
147
Output speed, tokens a second
81
262,144
Context window, tokens
262,144

Every fact side by side

Qwen3.5-122B-A10BMinistral 3 14B
Price per million tokens$0.26 in · $2.08 out$0.20 in · $0.20 out
Blended (3 in : 1 out)$0.72$0.20
Cheapest host, blended$0.72 (Alibaba)$0.20 (Mistral)
Cached input, per million–$0.020 cached input
Intelligence Index17.76.0
Spring Prompt overall––
Output speed, tokens a second14781
Context window262,144 tokens262,144 tokens
Released24 Feb 2026 (newer)2 Dec 2025
WeightsOpenOpen
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.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 95 of 164 131 of 164
Reasoning and knowledgeHard questions across science, maths and general knowledge 87 of 198 170 of 198
WritingWhat people prefer in blind comparisons, and judged writing quality 102 of 188 145 of 188
Sticking to the factsSummarising without inventing things, and factual answers 108 of 152 145 of 152

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-A10BMinistral 3 14B
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 114 · 229 of 243 measured 17.7no reasoning 6.0
GPQA Diamond% of questions, higher is better 75 · 191 of 231 measured 85.7% 57.2%
Humanity's Last Exam% of questions, higher is better 92 · 198 of 242 measured 25.2% 4.6%
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 112 · 148 of 230 measured 39.5no reasoning 31.4
Requested-length error · UGI% off the requested word count, lower is better 33 · 140 of 230 measured 9.0%thinking reasoning 24.0%
Style adherence · UGIscore from 0 to 1, higher is better 83 · 167 of 230 measured 0.36no reasoning 0.32
Vectara Hallucination Leaderboard reported by Vectara Hallucination Leaderboard · 2 results
Hallucination rate · Vectara% of summaries, lower is better 72 · 97 of 104 measured 11.2% 19.4%
Answer rate · Vectara% of documents, higher is better 31 · 45 of 104 measured 99.8% 99.6%
Show all 19 results (11 more)
MeasureQwen3.5-122B-A10BMinistral 3 14B
Artificial Analysis reported by Artificial Analysis · 11 results
Terminal-Bench 2.1% of tasks, higher is better 64 · 105 of 130 measured 47.6% 9.7%
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 58 · 93 of 121 measured 15.3% 6.6%
Artificial Analysis Coding Indexindex score, higher is better 65 · 113 of 131 measured 45.7 14.4
IFBench% of instructions, higher is better 22 · 171 of 195 measured 75.7% 32.0%
Long-context reasoning (AA-LCR)% of questions, higher is better 72 · 191 of 233 measured 76.3% 26.3%
Output speedtokens per second, higher is better 21 · 50 of 74 measured 147no reasoning 81.3
SciCode% of problems, higher is better 79 · 108 of 113 measured 39.7% 23.8%
Terminal-Bench Hard% of tasks, higher is better 65 · 156 of 190 measured 31.1% 4.5%
Time to first answer tokenseconds, lower is better 29 · 8 of 74 measured 1.05no reasoning 0.51
τ²-bench telecom% of tasks, higher is better 30 · 144 of 193 measured 93.6% 27.2%

Quick answers

Is Qwen3.5-122B-A10B better than Ministral 3 14B?

Pick Qwen3.5-122B-A10B if quality matters most: it scores higher (Intelligence Index 17.7 against 6.0). Pick Ministral 3 14B if cost matters more: it costs 3.6 times less per token. Qwen3.5-122B-A10B is also faster.

Which is cheaper, Qwen3.5-122B-A10B or Ministral 3 14B?

Ministral 3 14B is cheaper: $0.20 against $0.72 per million tokens, 3.6 times less.

Which is faster, Qwen3.5-122B-A10B or Ministral 3 14B?

Qwen3.5-122B-A10B writes about 147 tokens a second on its usual API, against 81 for Ministral 3 14B (Artificial Analysis).

Which is better for agents and tool use, Qwen3.5-122B-A10B or Ministral 3 14B?

Qwen3.5-122B-A10B ranks 95 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 131 for Ministral 3 14B.

Which is better for reasoning and knowledge, Qwen3.5-122B-A10B or Ministral 3 14B?

Qwen3.5-122B-A10B ranks 87 of 198 models on sale for hard questions across science, maths and general knowledge, against 170 for Ministral 3 14B.

Which is better for writing, Qwen3.5-122B-A10B or Ministral 3 14B?

Qwen3.5-122B-A10B ranks 102 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 145 for Ministral 3 14B.

Which is better for sticking to the facts, Qwen3.5-122B-A10B or Ministral 3 14B?

Qwen3.5-122B-A10B ranks 108 of 152 models on sale for summarising without inventing things, and factual answers, against 145 for Ministral 3 14B.

Run Qwen3.5-122B-A10B and Ministral 3 14B 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