Model comparison
DeepSeek-V2.5 (Sep 2024) vs Mistral Medium 3.5
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 37.6 on the Noometry Index.
Last verified . 16 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 16 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 1 category and Mistral Medium 3.5 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Mistral Medium 3.5 leads 51.9 to 42.5.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Mistral Medium 3.5 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 37.6 | 40.2 |
| Released | 2024-09-06 | — |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 210K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 22 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium 3.5 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Mistral Medium 3.5: 36.0 (#213)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Medium 3.5 |
|---|---|---|
| LMArena Coding | 1309 | 1461 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1264 |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Mistral Medium 3.5: 17.3 (#295)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Medium 3.5 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1436 |
| Kagi LLM Benchmark | — | 41.4% |
| NYT Connections (extended) | — | 12.9% |
| Epoch Capabilities Index | — | 141.35 |
Math Mistral Medium 3.5 leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Mistral Medium 3.5: 39.1 (#113)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1288 | 1431 |
Knowledge Mistral Medium 3.5 leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Mistral Medium 3.5: 40.0 (#126)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1266 | 1432 |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Mistral Medium 3.5: 38.3 (#65)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1223 |
Multilingual Mistral Medium 3.5 leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Mistral Medium 3.5: 51.9 (#100)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1273 | 1404 |
| LMArena Chinese | 1318 | 1442 |
| LMArena French | 1289 | 1448 |
| LMArena German | 1258 | 1451 |
| LMArena Korean | 1209 | 1385 |
| LMArena Russian | 1289 | 1395 |
| LMArena Spanish | 1248 | 1409 |
| LMArena Japanese | 1228 | — |
Instruction Following Mistral Medium 3.5 leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Mistral Medium 3.5: 74.6 (#90)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1415 |
Long Context Mistral Medium 3.5 leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Mistral Medium 3.5: 43.2 (#103)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1301 | 1415 |
Writing & Preference Mistral Medium 3.5 leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Mistral Medium 3.5: 58.5 (#117)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1294 | 1421 |
| LMArena Creative Writing | 1285 | 1374 |
| LMArena Multi-Turn | 1297 | 1423 |
| EQ-Bench 4 | — | 993 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Mistral Medium 3.5?
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Mistral Medium 3.5 better for coding?
Mistral Medium 3.5 scores higher on coding benchmarks: 36.0 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Mistral Medium 3.5 share?
16 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Mistral Medium 3.5 has 22.