Model comparison
Deepseek Coder v2 vs Ministral 3B
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 26.2 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
Mistral AISummary
- The widest gap is in knowledge, where Deepseek Coder v2 leads 32.3 to 10.4.
Side by side
| Deepseek Coder v2 | Ministral 3B | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 35.9 | 26.2 |
| Released | 2024-06-17 | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.10 |
| Results tracked | 24 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Deepseek Coder v2: 38.1 (#183), Ministral 3B: —
| Benchmark | Deepseek Coder v2 | Ministral 3B |
|---|---|---|
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1251 | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), Ministral 3B: 18.4 (#282)
| Benchmark | Deepseek Coder v2 | Ministral 3B |
|---|---|---|
| LMArena Hard Prompts | 1207 | — |
| DTBench | — | 51.7% |
| LMCA | — | 5.5% |
| Epoch Capabilities Index | — | 118.1 |
| WinoGrande | 83.7% | — |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 34.9 (#190), Ministral 3B: 26.6 (#258)
| Benchmark | Deepseek Coder v2 | Ministral 3B |
|---|---|---|
| LMArena Math | 1241 | — |
| MATH Level 5 | — | 14.4% |
| GSM8K | 94.5% | — |
Knowledge Deepseek Coder v2 leads
Deepseek Coder v2: 32.3 (#212), Ministral 3B: 10.4 (#302)
| Benchmark | Deepseek Coder v2 | Ministral 3B |
|---|---|---|
| GPQA Diamond | — | 25.3% |
| Vectara Hallucination Rate | — | 7.3% |
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Not comparable
Deepseek Coder v2: 36.3 (#240), Ministral 3B: —
| Benchmark | Deepseek Coder v2 | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1182 | — |
| LMArena Chinese | 1201 | — |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Not comparable
Deepseek Coder v2: 61.7 (#242), Ministral 3B: —
| Benchmark | Deepseek Coder v2 | Ministral 3B |
|---|---|---|
| LMArena Instruction Following | 1180 | — |
Long Context Not comparable
Deepseek Coder v2: 37.0 (#224), Ministral 3B: —
| Benchmark | Deepseek Coder v2 | Ministral 3B |
|---|---|---|
| LMArena Longer Query | 1219 | — |
Writing & Preference Not comparable
Deepseek Coder v2: 38.2 (#253), Ministral 3B: —
| Benchmark | Deepseek Coder v2 | Ministral 3B |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1120 | — |
| LMArena Multi-Turn | 1177 | — |
Frequently asked questions
Is Deepseek Coder v2 better than Ministral 3B?
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 26.2 on the Noometry Index.
How many benchmarks do Deepseek Coder v2 and Ministral 3B share?
0 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Ministral 3B has 6.