Model comparison
Ministral 3B vs Qwen2-72B
Qwen2-72B is the stronger model overall, scoring 30.0 to 26.2 on the Noometry Index.
Last verified . 3 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Ministral 3B scores higher in 0 categories and Qwen2-72B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2-72B leads 21.2 to 10.4.
- The biggest single-benchmark swing is MATH Level 5: 14.4% for Ministral 3B and 39.1% for Qwen2-72B.
Side by side
| Ministral 3B | Qwen2-72B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 26.2 | 30.0 |
| Released | 2024-10-01 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.10 | — |
| Results tracked | 6 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Ministral 3B: —, Qwen2-72B: 29.1 (#310)
| Benchmark | Ministral 3B | Qwen2-72B |
|---|---|---|
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| LMArena Coding | — | 1196 |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Ministral 3B: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Ministral 3B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Ministral 3B: 18.4 (#282), Qwen2-72B: 23.2 (#181)
| Benchmark | Ministral 3B | Qwen2-72B |
|---|---|---|
| Epoch Capabilities Index | 118.1 | 125.28 |
| LMArena Hard Prompts | — | 1191 |
| DTBench | 51.7% | — |
| LMCA | 5.5% | — |
Math Qwen2-72B leads
Ministral 3B: 26.6 (#258), Qwen2-72B: 30.2 (#236)
| Benchmark | Ministral 3B | Qwen2-72B |
|---|---|---|
| MATH Level 5 | 14.4% | 39.1% |
| LMArena Math | — | 1235 |
Knowledge Qwen2-72B leads
Ministral 3B: 10.4 (#302), Qwen2-72B: 21.2 (#275)
| Benchmark | Ministral 3B | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 25.3% | 40.8% |
| Vectara Hallucination Rate | 7.3% | — |
| LMArena Expert | — | 1171 |
| MMLU | — | 82.4% |
Multilingual Not comparable
Ministral 3B: —, Qwen2-72B: 35.9 (#244)
| Benchmark | Ministral 3B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | — | 1176 |
| LMArena Chinese | — | 1240 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1169 |
Instruction Following Not comparable
Ministral 3B: —, Qwen2-72B: 61.7 (#241)
| Benchmark | Ministral 3B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | — | 1181 |
Long Context Not comparable
Ministral 3B: —, Qwen2-72B: 36.1 (#235)
| Benchmark | Ministral 3B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1192 |
Writing & Preference Not comparable
Ministral 3B: —, Qwen2-72B: 40.8 (#241)
| Benchmark | Ministral 3B | Qwen2-72B |
|---|---|---|
| LMArena Text | — | 1203 |
| LMArena Creative Writing | — | 1181 |
| LMArena Multi-Turn | — | 1196 |
Frequently asked questions
Is Ministral 3B better than Qwen2-72B?
Qwen2-72B is the stronger model overall, scoring 30.0 to 26.2 on the Noometry Index.
How many benchmarks do Ministral 3B and Qwen2-72B share?
3 benchmarks have published results for both models. Ministral 3B has 6 scored results on Noometry and Qwen2-72B has 26.