Model comparison
Ministral 3B vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 38.8 to 25.6 on the Noometry Index. Ministral 3B costs 31× less per token, which makes it the better buy when Qwen3 32B's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. Ministral 3B scores higher in 0 categories and Qwen3 32B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 32B leads 40.0 to 10.4.
- The biggest single-benchmark swing is GPQA Diamond: 25.3% for Ministral 3B and 65.7% for Qwen3 32B.
- Ministral 3B is cheaper at $0.04 / $0.04 per million input/output tokens, against $0.70 / $2.80 for Qwen3 32B.
- Qwen3 32B accepts more context: 131K tokens versus 128K.
Side by side
| Ministral 3B | Qwen3 32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 25.6 | 38.8 |
| Released | 2024-10-01 | 2025-04 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 128K | 16K |
| Input $ / M tokens | $0.04 | $0.70 |
| Output $ / M tokens | $0.04 | $2.80 |
| Results tracked | 6 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Ministral 3B: —, Qwen3 32B: 37.3 (#184)
| Benchmark | Ministral 3B | Qwen3 32B |
|---|---|---|
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| LMArena Coding | — | 1358 |
Agentic & Tool Use Not comparable
Ministral 3B: —, Qwen3 32B: 32.3 (#58)
| Benchmark | Ministral 3B | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Qwen3 32B leads
Ministral 3B: 17.7 (#278), Qwen3 32B: 19.6 (#233)
| Benchmark | Ministral 3B | Qwen3 32B |
|---|---|---|
| DTBench | 51.7% | 67.5% |
| LMCA | 5.5% | 17.3% |
| Epoch Capabilities Index | 118.08 | 138.51 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| LMArena Hard Prompts | — | 1335 |
Math Qwen3 32B leads
Ministral 3B: 24.5 (#257), Qwen3 32B: 37.9 (#89)
| Benchmark | Ministral 3B | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| LMArena Math | — | 1399 |
| MATH Level 5 | 14.4% | — |
Knowledge Qwen3 32B leads
Ministral 3B: 10.4 (#297), Qwen3 32B: 40.0 (#112)
| Benchmark | Ministral 3B | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 25.3% | 65.7% |
| Vectara Hallucination Rate | 7.3% | 5.9% |
| LMArena Expert | — | 1362 |
Multilingual Not comparable
Ministral 3B: —, Qwen3 32B: 45.8 (#162)
| Benchmark | Ministral 3B | Qwen3 32B |
|---|---|---|
| LMArena Non-English | — | 1317 |
| LMArena Chinese | — | 1357 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1311 |
Instruction Following Not comparable
Ministral 3B: —, Qwen3 32B: 69.1 (#174)
| Benchmark | Ministral 3B | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | — | 1305 |
Long Context Not comparable
Ministral 3B: —, Qwen3 32B: 43.7 (#83)
| Benchmark | Ministral 3B | Qwen3 32B |
|---|---|---|
| Fiction.LiveBench | — | 74.2% |
| LMArena Longer Query | — | 1327 |
Writing & Preference Not comparable
Ministral 3B: —, Qwen3 32B: 53.1 (#158)
| Benchmark | Ministral 3B | Qwen3 32B |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1297 |
| LMArena Multi-Turn | — | 1331 |
Frequently asked questions
Is Ministral 3B better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 38.8 to 25.6 on the Noometry Index. Ministral 3B costs 31× less per token, which makes it the better buy when Qwen3 32B's lead doesn't matter for your workload.
Which is cheaper, Ministral 3B or Qwen3 32B?
Ministral 3B is cheaper. It lists at $0.04 per million input tokens and $0.04 per million output tokens; Qwen3 32B lists at $0.70 and $2.80.
Which has the bigger context window?
Qwen3 32B does, with 131K tokens against 128K.
How many benchmarks do Ministral 3B and Qwen3 32B share?
5 benchmarks have published results for both models. Ministral 3B has 6 scored results on Noometry and Qwen3 32B has 26.