Compare / Qwen3.5-35B-A3B vs Ministral 3 8B
Qwen3.5-35B-A3B vs Ministral 3 8B
Which is cheaper, which is more capable, and which does better at each kind of work, from 15 results on 3 sources that measured both models.
Of the 15 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.
Qwen3.5-35B-A3B or Ministral 3 8B? The short answer
Pick Qwen3.5-35B-A3B if quality matters most: it scores higher (Intelligence Index 19.3 against 5.5). Pick Ministral 3 8B if cost matters more: it costs 3.0 times less per token.
- Ministral 3 8B is cheaper: $0.15 against $0.45 per million tokens, 3.0 times less.
- Qwen3.5-35B-A3B scores higher on the Artificial Analysis Intelligence Index: 19.3 against 5.5.
- Qwen3.5-35B-A3B is newer: released 24 Feb 2026, against 2 Dec 2025 for Ministral 3 8B.
- On third-party benchmarks, on the results both models have: Qwen3.5-35B-A3B does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.
Head to head
Every fact side by side
| Qwen3.5-35B-A3B | Ministral 3 8B | |
|---|---|---|
| Price per million tokens | $0.16 in · $1.30 out | $0.15 in · $0.15 out |
| Blended (3 in : 1 out) | $0.45 | $0.15 |
| Cheapest host, blended | $0.25 (Darkbloom, FP4) | $0.15 (Mistral) |
| Cached input, per million | – | $0.015 cached input |
| Intelligence Index | 19.3 | 5.5 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | 102 |
| Context window | 262,144 tokens | 262,144 tokens |
| Released | 24 Feb 2026 (newer) | 2 Dec 2025 |
| Weights | Open | Open |
| Developer based in | China | France |
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.
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.
| Measure | Qwen3.5-35B-A3B | Ministral 3 8B |
|---|---|---|
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 108 · 237 of 243 measured | 19.3 | 5.5 |
| GPQA Diamond% of questions, higher is better 84 · 208 of 231 measured | 84.5% | 47.1% |
| Humanity's Last Exam% of questions, higher is better 106 · 209 of 242 measured | 21.0% | 4.3% |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 97 · 160 of 230 measured | 42.6think-prefill reasoning | 28.8 |
| Requested-length error · UGI% off the requested word count, lower is better 83 · 134 of 230 measured | 17.0%no reasoning | 23.0% |
| Style adherence · UGIscore from 0 to 1, higher is better 151 · 140 of 230 measured | 0.33no reasoning | 0.33think-prefill reasoning |
| Vectara Hallucination Leaderboard reported by Vectara Hallucination Leaderboard · 2 results | ||
| Hallucination rate · Vectara% of summaries, lower is better 62 · 100 of 104 measured | 10.5% | 21.7% |
| Answer rate · Vectara% of documents, higher is better 31 · 61 of 104 measured | 99.8% | 99.1% |
Show all 15 results (7 more)
| Measure | Qwen3.5-35B-A3B | Ministral 3 8B |
|---|---|---|
| Artificial Analysis reported by Artificial Analysis · 7 results | ||
| Terminal-Bench 2.1% of tasks, higher is better 72 · 117 of 130 measured | 40.8%no reasoning | 4.1% |
| τ-bench banking% of tasks, higher is better 107 · 114 of 121 measured | 4.9%no reasoning | 3.7% |
| Artificial Analysis Coding Indexindex score, higher is better 79 · 122 of 131 measured | 37.0no reasoning | 9.7 |
| IFBench% of instructions, higher is better 39 · 185 of 195 measured | 72.5% | 29.1% |
| Long-context reasoning (AA-LCR)% of questions, higher is better 99 · 193 of 233 measured | 72.0% | 25.7% |
| Terminal-Bench Hard% of tasks, higher is better 74 · 156 of 190 measured | 26.5% | 4.5% |
| τ²-bench telecom% of tasks, higher is better 45 · 146 of 193 measured | 89.2% | 26.6% |
Compare them with other models
Quick answers
Is Qwen3.5-35B-A3B better than Ministral 3 8B?
Pick Qwen3.5-35B-A3B if quality matters most: it scores higher (Intelligence Index 19.3 against 5.5). Pick Ministral 3 8B if cost matters more: it costs 3.0 times less per token.
Which is cheaper, Qwen3.5-35B-A3B or Ministral 3 8B?
Ministral 3 8B is cheaper: $0.15 against $0.45 per million tokens, 3.0 times less.
Which is better for agents and tool use, Qwen3.5-35B-A3B or Ministral 3 8B?
Qwen3.5-35B-A3B ranks 116 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 153 for Ministral 3 8B.
Which is better for reasoning and knowledge, Qwen3.5-35B-A3B or Ministral 3 8B?
Qwen3.5-35B-A3B ranks 92 of 198 models on sale for hard questions across science, maths and general knowledge, against 187 for Ministral 3 8B.
Which is better for writing, Qwen3.5-35B-A3B or Ministral 3 8B?
Qwen3.5-35B-A3B ranks 108 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 157 for Ministral 3 8B.
Which is better for sticking to the facts, Qwen3.5-35B-A3B or Ministral 3 8B?
Qwen3.5-35B-A3B ranks 112 of 152 models on sale for summarising without inventing things, and factual answers, against 146 for Ministral 3 8B.
Run Qwen3.5-35B-A3B and Ministral 3 8B on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.