Model comparison
Deepseek Coder v2 vs Mistral Large
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 31.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 21 benchmarks with published results for both. Deepseek Coder v2 scores higher in 4 categories and Mistral Large in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Deepseek Coder v2 leads 34.9 to 18.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 59.7% for Deepseek Coder v2 and 38.3% for Mistral Large.
Side by side
| Deepseek Coder v2 | Mistral Large | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 35.9 | 31.9 |
| Released | 2024-06-17 | 2024-02-26 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 24 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Deepseek Coder v2: 38.1 (#183), Mistral Large: 34.3 (#240)
| Benchmark | Deepseek Coder v2 | Mistral Large |
|---|---|---|
| BigCodeBench Instruct | 48.2% | 30% |
| LMArena Coding | 1251 | 1277 |
| BigCodeBench Complete | 59.7% | 38.3% |
| HumanEval+ | 82.3% | 62.2% |
| MBPP+ | 75.1% | 59.5% |
| SciCode | — | 36.2% |
| LiveBench Coding | — | 47.1% |
| ALE-Bench | — | 264.7 |
Agentic & Tool Use Not comparable
Deepseek Coder v2: —, Mistral Large: 28.6 (#89)
| Benchmark | Deepseek Coder v2 | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), Mistral Large: 15.8 (#310)
| Benchmark | Deepseek Coder v2 | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1257 |
| SimpleBench | — | 22.5% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| Epoch Capabilities Index | — | 128.52 |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
| WinoGrande | 83.7% | — |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 34.9 (#190), Mistral Large: 18.2 (#291)
| Benchmark | Deepseek Coder v2 | Mistral Large |
|---|---|---|
| LMArena Math | 1241 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
| GSM8K | 94.5% | — |
Knowledge Deepseek Coder v2 leads
Deepseek Coder v2: 32.3 (#212), Mistral Large: 30.1 (#230)
| Benchmark | Deepseek Coder v2 | Mistral Large |
|---|---|---|
| LMArena Expert | 1181 | 1232 |
| GPQA Diamond | — | 51.3% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| ARC (AI2) Challenge | 64.3% | — |
| MMLU | — | 80% |
Multilingual Mistral Large leads
Deepseek Coder v2: 36.3 (#240), Mistral Large: 40.0 (#219)
| Benchmark | Deepseek Coder v2 | Mistral Large |
|---|---|---|
| LMArena Non-English | 1182 | 1237 |
| LMArena Chinese | 1201 | 1240 |
| LMArena French | 1185 | 1325 |
| LMArena German | 1164 | 1254 |
| LMArena Japanese | 1126 | 1188 |
| LMArena Korean | 1104 | 1202 |
| LMArena Russian | 1188 | 1257 |
| LMArena Spanish | 1153 | 1268 |
Instruction Following Mistral Large leads
Deepseek Coder v2: 61.7 (#242), Mistral Large: 67.9 (#191)
| Benchmark | Deepseek Coder v2 | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1180 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context Mistral Large leads
Deepseek Coder v2: 37.0 (#224), Mistral Large: 38.3 (#199)
| Benchmark | Deepseek Coder v2 | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1219 | 1261 |
Writing & Preference Mistral Large leads
Deepseek Coder v2: 38.2 (#253), Mistral Large: 40.7 (#242)
| Benchmark | Deepseek Coder v2 | Mistral Large |
|---|---|---|
| LMArena Text | 1191 | 1266 |
| LMArena Creative Writing | 1120 | 1243 |
| LMArena Multi-Turn | 1177 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Deepseek Coder v2 better than Mistral Large?
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 31.9 on the Noometry Index.
Is Deepseek Coder v2 or Mistral Large better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 34.3 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Mistral Large share?
21 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Mistral Large has 51.