Compare / Qwen3 14B vs Mistral Small 3.2 24B
Qwen3 14B vs Mistral Small 3.2 24B
Which is cheaper, which is more capable, and which does better at each kind of work, from 23 results on 3 sources that measured both models.
Qwen3 14B or Mistral Small 3.2 24B? The short answer
- Mistral Small 3.2 24B is cheaper: $0.13 against $0.15 per million tokens, 11% less.
- They score about the same on the Artificial Analysis Intelligence Index (8.2 and 8.2).
- On our business benchmarks, Qwen3 14B ranks higher for reasoning and knowledge and writing.
- On our business benchmarks, Mistral Small 3.2 24B ranks higher for agents and tool use.
At a glance
| Qwen3 14B | Mistral Small 3.2 24B | |
|---|---|---|
| Price per million tokens | $0.12 in · $0.24 out | $0.094 in · $0.25 out |
| Blended (3 in : 1 out) | $0.15 | $0.13 |
| Cheapest host, blended | $0.13 (NextBit, INT4) | $0.11 (DeepInfra, FP8) |
| Intelligence Index | 8.2 | 8.2 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 131,072 tokens | 256,000 tokens |
| 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 models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | Qwen3 14B | Mistral Small 3.2 24B |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 120 of 161 | 118 of 161 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 159 of 195 | 163 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 128 of 187 | 130 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 17 of 153 | not measured |
Every shared result
| Benchmark | Metric | Qwen3 14B | Mistral Small 3.2 24B |
|---|---|---|---|
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 13.8 | 12.5 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 8.20 | 8.20 |
| Artificial Analysisreported | GPQA Diamond% of questions | 60.4% | 50.5% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 4.5% | 4.3% |
| Artificial Analysisreported | IFBench% of instructions | 40.5% | 33.5% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 0.0% | 20.3% |
| Artificial Analysisreported | SciCode% of problems | 30.7% | 28.6% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 4.9% | 5.6% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 0.0% | 0.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 5.3% | 6.8% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 5.6% | 6.2% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 34.5% | 29.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 87.2% | 87.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 19.6% | 18.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 34.8% | 14.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 41.0% | 37.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 87.5% | 93.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 89.5% | 89.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 80.0% | 79.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 10.5% | 31.0% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 20.0% | 17.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.37 | 0.35 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 34.8 | 36.3 |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.
Quick answers
Is Qwen3 14B better than Mistral Small 3.2 24B?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Qwen3 14B ranks higher for reasoning and knowledge and writing; Mistral Small 3.2 24B ranks higher for agents and tool use.
Which is cheaper, Qwen3 14B or Mistral Small 3.2 24B?
Mistral Small 3.2 24B costs $0.13 per million tokens (three input to one output), against $0.15 for Qwen3 14B.
Run Qwen3 14B 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.