Model comparison
Ministral 3B vs Qwen2.5 32B Instruct
Qwen2.5 32B Instruct is the stronger model overall, scoring 29.7 to 25.6 on the Noometry Index. Ministral 3B costs 31× less per token, which makes it the better buy when Qwen2.5 32B Instruct's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Ministral 3B scores higher in 1 category and Qwen2.5 32B Instruct in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5 32B Instruct leads 24.9 to 10.4.
- The biggest single-benchmark swing is MATH Level 5: 14.4% for Ministral 3B and 56.1% for Qwen2.5 32B Instruct.
- Ministral 3B is cheaper at $0.04 / $0.04 per million input/output tokens, against $0.70 / $2.80 for Qwen2.5 32B Instruct.
- Qwen2.5 32B Instruct accepts more context: 131K tokens versus 128K.
Side by side
| Ministral 3B | Qwen2.5 32B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 25.6 | 29.7 |
| Released | 2024-10-01 | 2024-09 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 128K | 8K |
| Input $ / M tokens | $0.04 | $0.70 |
| Output $ / M tokens | $0.04 | $2.80 |
| Results tracked | 6 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Ministral 3B: —, Qwen2.5 32B Instruct: 38.1 (#165)
| Benchmark | Ministral 3B | Qwen2.5 32B Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 45% |
| BigCodeBench Complete | — | 52.3% |
Reasoning Too close to call
Ministral 3B: 17.7 (#278), Qwen2.5 32B Instruct: 18.5 (#262)
| Benchmark | Ministral 3B | Qwen2.5 32B Instruct |
|---|---|---|
| Epoch Capabilities Index | 118.08 | 128.52 |
| Chess Puzzles | — | 0% |
| DTBench | 51.7% | — |
| LMCA | 5.5% | — |
Math Ministral 3B leads
Ministral 3B: 24.5 (#257), Qwen2.5 32B Instruct: 15.3 (#289)
| Benchmark | Ministral 3B | Qwen2.5 32B Instruct |
|---|---|---|
| MATH Level 5 | 14.4% | 56.1% |
| OTIS Mock AIME 2024-2025 | — | 7.4% |
Knowledge Qwen2.5 32B Instruct leads
Ministral 3B: 10.4 (#297), Qwen2.5 32B Instruct: 24.9 (#259)
| Benchmark | Ministral 3B | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | 25.3% | 46.1% |
| Vectara Hallucination Rate | 7.3% | — |
Frequently asked questions
Is Ministral 3B better than Qwen2.5 32B Instruct?
Qwen2.5 32B Instruct is the stronger model overall, scoring 29.7 to 25.6 on the Noometry Index. Ministral 3B costs 31× less per token, which makes it the better buy when Qwen2.5 32B Instruct's lead doesn't matter for your workload.
Which is cheaper, Ministral 3B or Qwen2.5 32B Instruct?
Ministral 3B is cheaper. It lists at $0.04 per million input tokens and $0.04 per million output tokens; Qwen2.5 32B Instruct lists at $0.70 and $2.80.
Which has the bigger context window?
Qwen2.5 32B Instruct does, with 131K tokens against 128K.
How many benchmarks do Ministral 3B and Qwen2.5 32B Instruct share?
3 benchmarks have published results for both models. Ministral 3B has 6 scored results on Noometry and Qwen2.5 32B Instruct has 7.