Compare / Qwen3-32B vs Mistral Small 3.2 24B
Qwen3-32B vs Mistral Small 3.2 24B
Which is cheaper, which is more capable, and which does better at each kind of work, from 29 results on 4 sources that measured both models.
Of the 29 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.
Qwen3-32B or Mistral Small 3.2 24B? The short answer
They score about the same, so pick Mistral Small 3.2 24B: it costs 35% less per token.
- Mistral Small 3.2 24B is cheaper: $0.13 against $0.21 per million tokens, 35% less.
- They score about the same on the Artificial Analysis Intelligence Index (8.6 and 8.2).
- Mistral Small 3.2 24B is newer: released 20 Jun 2025, against 28 Apr 2025 for Qwen3-32B.
- On third-party benchmarks, on the results both models have: Qwen3-32B does better for reasoning and knowledge; Mistral Small 3.2 24B for agents and tool use and writing.
Head to head
Every fact side by side
| Qwen3-32B | Mistral Small 3.2 24B | |
|---|---|---|
| Price per million tokens | $0.14 in · $0.40 out | $0.094 in · $0.25 out |
| Blended (3 in : 1 out) | $0.21 | $0.13 |
| Cheapest host, blended | $0.13 (DeepInfra, FP8) | $0.11 (DeepInfra, FP8) |
| Intelligence Index | 8.6 | 8.2 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 131,072 tokens | 256,000 tokens |
| Released | 28 Apr 2025 | 20 Jun 2025 (newer) |
| 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.
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.
| Measure | Qwen3-32B | Mistral Small 3.2 24B |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 195 · 182 of 387 measured | 1,347 | 1,356 |
| Business, management and finance · TextArena rating, higher is better 203 · 178 of 380 measured | 1,340 | 1,363 |
| Creative writing · TextArena rating, higher is better 205 · 182 of 385 measured | 1,304 | 1,324 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 188 · 194 of 243 measured | 8.6thinking reasoning | 8.2 |
| GPQA Diamond% of questions, higher is better 167 · 201 of 231 measured | 66.8%thinking reasoning | 50.5% |
| Humanity's Last Exam% of questions, higher is better 168 · 209 of 242 measured | 7.4%thinking reasoning | 4.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4 reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 3 results | ||
| Overall accuracy · BFCL% correct, higher is better 24 · 38 of 81 measured | 48.7%bfcl fc | 37.2%bfcl fc |
| Irrelevance detection · BFCL% correct, higher is better 37 · 15 of 81 measured | 82.4%bfcl prompt | 87.9%bfcl fc |
| Memory · BFCL% correct, higher is better 21 · 37 of 81 measured | 26.7%bfcl fc | 18.1%bfcl fc |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 134 · 122 of 230 measured | 33.0no reasoning | 36.3 |
| Requested-length error · UGI% off the requested word count, lower is better 99 · 83 of 230 measured | 19.0%no reasoning | 17.0% |
| Style adherence · UGIscore from 0 to 1, higher is better 175 · 104 of 230 measured | 0.32no reasoning | 0.35 |
Show all 29 results (17 more)
| Measure | Qwen3-32B | Mistral Small 3.2 24B |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Expert prompts · TextArena rating, higher is better 159 · 205 of 338 measured | 1,398 | 1,334 |
| Instruction following · TextArena rating, higher is better 198 · 192 of 387 measured | 1,331 | 1,338 |
| Writing, literature and language · TextArena rating, higher is better 217 · 192 of 386 measured | 1,308 | 1,329 |
| Artificial Analysis reported by Artificial Analysis · 9 results | ||
| Terminal-Bench 2.1% of tasks, higher is better 111 · 109 of 130 measured | 5.2%thinking reasoning | 5.6% |
| Terminal-Bench 4.0% of tasks, higher is better 66 · 66 of 112 measured | 0.0%thinking reasoning | 0.0% |
| τ-bench banking% of tasks, higher is better 102 · 95 of 121 measured | 5.4%thinking reasoning | 6.2% |
| Artificial Analysis Coding Indexindex score, higher is better 111 · 116 of 131 measured | 15.3thinking reasoning | 12.5 |
| IFBench% of instructions, higher is better 155 · 165 of 195 measured | 36.3%thinking reasoning | 33.5% |
| Long-context reasoning (AA-LCR)% of questions, higher is better 222 · 201 of 233 measured | 0.0%no reasoning | 20.3% |
| SciCode% of problems, higher is better 91 · 103 of 113 measured | 36.0%thinking reasoning | 28.6% |
| Terminal-Bench Hard% of tasks, higher is better 169 · 140 of 190 measured | 3.0%thinking reasoning | 6.8% |
| τ²-bench telecom% of tasks, higher is better 135 · 136 of 193 measured | 29.8%thinking reasoning | 29.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4 reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 5 results | ||
| Multi-turn tasks · BFCL% correct, higher is better 17 · 45 of 81 measured | 47.9%bfcl fc | 14.8%bfcl prompt |
| Relevance detection · BFCL% correct, higher is better 8 · 8 of 81 measured | 93.8%bfcl fc | 93.8%bfcl prompt |
| Single-turn calls (curated) · BFCL% correct, higher is better 3 · 4 of 81 measured | 90.3%bfcl prompt | 89.7%bfcl prompt |
| Single-turn calls (user-contributed) · BFCL% correct, higher is better 3 · 13 of 81 measured | 82.0%bfcl fc | 79.1%bfcl prompt |
| Web search · BFCL% correct, higher is better 28 · 24 of 81 measured | 26.0%bfcl prompt | 31.0%bfcl fc |
Compare them with other models
Quick answers
Is Qwen3-32B better than Mistral Small 3.2 24B?
They score about the same, so pick Mistral Small 3.2 24B: it costs 35% less per token.
Which is cheaper, Qwen3-32B or Mistral Small 3.2 24B?
Mistral Small 3.2 24B is cheaper: $0.13 against $0.21 per million tokens, 35% less.
Which is better for agents and tool use, Qwen3-32B or Mistral Small 3.2 24B?
Qwen3-32B ranks 113 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 119 for Mistral Small 3.2 24B.
Which is better for reasoning and knowledge, Qwen3-32B or Mistral Small 3.2 24B?
Qwen3-32B ranks 148 of 198 models on sale for hard questions across science, maths and general knowledge, against 166 for Mistral Small 3.2 24B.
Which is better for writing, Qwen3-32B or Mistral Small 3.2 24B?
Mistral Small 3.2 24B ranks 132 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 139 for Qwen3-32B.
Which has the bigger context window, Qwen3-32B or Mistral Small 3.2 24B?
Mistral Small 3.2 24B: 256,000 tokens, against 131,072 for Qwen3-32B.
Run Qwen3-32B and Mistral Small 3.2 24B on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.