Model comparison
Deepseek Coder v2 vs Mistral Medium
Deepseek Coder v2 and Mistral Medium score almost the same on the Noometry Index (35.9 vs 36.3), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 3 categories and Mistral Medium in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 38.2.
Side by side
| Deepseek Coder v2 | Mistral Medium | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 35.9 | 36.3 |
| Released | 2024-06-17 | 2023-12-11 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 24 | 36 |
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 Medium: 34.2 (#243)
| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Coding | 1251 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| ALE-Bench | — | 763.98 |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Agentic & Tool Use Not comparable
Deepseek Coder v2: —, Mistral Medium: 28.3 (#90)
| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Too close to call
Deepseek Coder v2: 23.6 (#176), Mistral Medium: 24.0 (#167)
| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| WinoGrande | 83.7% | — |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 34.9 (#190), Mistral Medium: 28.1 (#245)
| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Math | 1241 | 1408 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
| GSM8K | 94.5% | — |
Knowledge Deepseek Coder v2 leads
Deepseek Coder v2: 32.3 (#212), Mistral Medium: 25.0 (#265)
| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Expert | 1181 | 1408 |
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
| ARC (AI2) Challenge | 64.3% | — |
Multimodal Not comparable
Deepseek Coder v2: —, Mistral Medium: 35.3 (#88)
| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Mistral Medium leads
Deepseek Coder v2: 36.3 (#240), Mistral Medium: 52.1 (#91)
| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1182 | 1408 |
| LMArena Chinese | 1201 | 1447 |
| LMArena French | 1185 | 1459 |
| LMArena German | 1164 | 1432 |
| LMArena Japanese | 1126 | 1378 |
| LMArena Korean | 1104 | 1380 |
| LMArena Russian | 1188 | 1411 |
| LMArena Spanish | 1153 | 1433 |
Instruction Following Mistral Medium leads
Deepseek Coder v2: 61.7 (#242), Mistral Medium: 73.7 (#116)
| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1180 | 1398 |
Long Context Mistral Medium leads
Deepseek Coder v2: 37.0 (#224), Mistral Medium: 42.9 (#114)
| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1219 | 1406 |
Writing & Preference Mistral Medium leads
Deepseek Coder v2: 38.2 (#253), Mistral Medium: 60.0 (#103)
| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Text | 1191 | 1424 |
| LMArena Creative Writing | 1120 | 1391 |
| LMArena Multi-Turn | 1177 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
Frequently asked questions
Is Deepseek Coder v2 better than Mistral Medium?
Deepseek Coder v2 and Mistral Medium score almost the same on the Noometry Index (35.9 vs 36.3), so choose on price, context window or the category you care about most.
Is Deepseek Coder v2 or Mistral Medium better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 34.2 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Mistral Medium share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Mistral Medium has 36.