Model comparison
DeepSeek-V2.5 (Sep 2024) vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 1 category and Mistral Large 3 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V2.5 (Sep 2024) leads 25.6 to 15.2.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Mistral Large 3 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 37.6 | 39.1 |
| Released | 2024-09-06 | 2025-12-02 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.75 |
| Results tracked | 22 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 3 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Mistral Large 3: 34.4 (#237)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1309 | 1448 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1230 |
| 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 3: 15.2 (#319)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| Thematic Generalization | — | 23% |
Math Mistral Large 3 leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Mistral Large 3: 38.7 (#129)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1288 | 1414 |
Knowledge Mistral Large 3 leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Mistral Large 3: 36.0 (#177)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1266 | 1421 |
| Vectara Hallucination Rate | — | 14.5% |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Mistral Large 3: 38.2 (#66)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Mistral Large 3 leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Mistral Large 3: 52.5 (#84)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1273 | 1413 |
| LMArena Chinese | 1318 | 1447 |
| LMArena French | 1289 | 1455 |
| LMArena German | 1258 | 1437 |
| LMArena Japanese | 1228 | 1394 |
| LMArena Korean | 1209 | 1384 |
| LMArena Russian | 1289 | 1411 |
| LMArena Spanish | 1248 | 1440 |
Instruction Following Mistral Large 3 leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Mistral Large 3: 74.0 (#108)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1403 |
Long Context Mistral Large 3 leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Mistral Large 3: 43.1 (#105)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1301 | 1413 |
Writing & Preference Mistral Large 3 leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Mistral Large 3: 60.0 (#101)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1294 | 1428 |
| LMArena Creative Writing | 1285 | 1386 |
| LMArena Multi-Turn | 1297 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Mistral Large 3 better for coding?
Mistral Large 3 scores higher on coding benchmarks: 34.4 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Mistral Large 3 share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Mistral Large 3 has 24.