Model comparison
Deepseek Coder v2 vs Mistral Large 4
Mistral Large 4 is the stronger model overall, scoring 43.1 to 35.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 12 benchmarks with published results for both. Deepseek Coder v2 scores higher in 1 category and Mistral Large 4 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 4 leads 60.4 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Mistral Large 4 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 35.9 | 43.1 |
| Released | 2024-06-17 | 2026-10-06 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.68 |
| Output $ / M tokens | — | $2.09 |
| Results tracked | 24 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 4 leads
Deepseek Coder v2: 38.1 (#183), Mistral Large 4: 48.6 (#57)
| Benchmark | Deepseek Coder v2 | Mistral Large 4 |
|---|---|---|
| LMArena Coding | 1251 | 1475 |
| LMArena WebDev | — | 1541 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), Mistral Large 4: 22.5 (#192)
| Benchmark | Deepseek Coder v2 | Mistral Large 4 |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1444 |
| NYT Connections (extended) | — | 27.4% |
| WinoGrande | 83.7% | — |
Math Mistral Large 4 leads
Deepseek Coder v2: 34.9 (#190), Mistral Large 4: 40.4 (#91)
| Benchmark | Deepseek Coder v2 | Mistral Large 4 |
|---|---|---|
| LMArena Math | 1241 | 1488 |
| GSM8K | 94.5% | — |
Knowledge Mistral Large 4 leads
Deepseek Coder v2: 32.3 (#212), Mistral Large 4: 36.6 (#166)
| Benchmark | Deepseek Coder v2 | Mistral Large 4 |
|---|---|---|
| LMArena Expert | 1181 | 1447 |
| SimpleQA Verified | — | 20% |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Mistral Large 4 leads
Deepseek Coder v2: 36.3 (#240), Mistral Large 4: 52.6 (#82)
| Benchmark | Deepseek Coder v2 | Mistral Large 4 |
|---|---|---|
| LMArena Non-English | 1182 | 1415 |
| LMArena Chinese | 1201 | 1491 |
| LMArena Russian | 1188 | 1414 |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Mistral Large 4 leads
Deepseek Coder v2: 61.7 (#242), Mistral Large 4: 75.0 (#76)
| Benchmark | Deepseek Coder v2 | Mistral Large 4 |
|---|---|---|
| LMArena Instruction Following | 1180 | 1424 |
Long Context Mistral Large 4 leads
Deepseek Coder v2: 37.0 (#224), Mistral Large 4: 43.6 (#89)
| Benchmark | Deepseek Coder v2 | Mistral Large 4 |
|---|---|---|
| LMArena Longer Query | 1219 | 1429 |
Writing & Preference Mistral Large 4 leads
Deepseek Coder v2: 38.2 (#253), Mistral Large 4: 60.4 (#97)
| Benchmark | Deepseek Coder v2 | Mistral Large 4 |
|---|---|---|
| LMArena Text | 1191 | 1427 |
| LMArena Creative Writing | 1120 | 1361 |
| LMArena Multi-Turn | 1177 | 1424 |
Frequently asked questions
Is Deepseek Coder v2 better than Mistral Large 4?
Mistral Large 4 is the stronger model overall, scoring 43.1 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Mistral Large 4 better for coding?
Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Mistral Large 4 share?
12 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Mistral Large 4 has 15.