Model comparison
DeepSeek-V2.5 (Sep 2024) vs Mistral Large 4
Mistral Large 4 is the stronger model overall, scoring 43.1 to 37.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 12 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 1 category and Mistral Large 4 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mistral Large 4 leads 48.6 to 31.7.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Mistral Large 4 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 37.6 | 43.1 |
| Released | 2024-09-06 | 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 | 22 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 4 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Mistral Large 4: 48.6 (#57)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 4 |
|---|---|---|
| LMArena Coding | 1309 | 1475 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1541 |
| 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 Large 4: 22.5 (#192)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 4 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1444 |
| NYT Connections (extended) | — | 27.4% |
Math Mistral Large 4 leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Mistral Large 4: 40.4 (#91)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 4 |
|---|---|---|
| LMArena Math | 1288 | 1488 |
Knowledge Mistral Large 4 leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Mistral Large 4: 36.6 (#166)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 4 |
|---|---|---|
| LMArena Expert | 1266 | 1447 |
| SimpleQA Verified | — | 20% |
Multilingual Mistral Large 4 leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Mistral Large 4: 52.6 (#82)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 4 |
|---|---|---|
| LMArena Non-English | 1273 | 1415 |
| LMArena Chinese | 1318 | 1491 |
| LMArena Russian | 1289 | 1414 |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |
Instruction Following Mistral Large 4 leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Mistral Large 4: 75.0 (#76)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 4 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1424 |
Long Context Mistral Large 4 leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Mistral Large 4: 43.6 (#89)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 4 |
|---|---|---|
| LMArena Longer Query | 1301 | 1429 |
Writing & Preference Mistral Large 4 leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Mistral Large 4: 60.4 (#97)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 4 |
|---|---|---|
| LMArena Text | 1294 | 1427 |
| LMArena Creative Writing | 1285 | 1361 |
| LMArena Multi-Turn | 1297 | 1424 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Mistral Large 4?
Mistral Large 4 is the stronger model overall, scoring 43.1 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Mistral Large 4 better for coding?
Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Mistral Large 4 share?
12 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Mistral Large 4 has 15.