Model comparison
DeepSeek LLM 67B vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and Mistral Large 3 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Large 3 leads 38.7 to 8.7.
Side by side
| DeepSeek LLM 67B | Mistral Large 3 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 24.9 | 39.1 |
| Released | 2023-11-29 | 2025-12-02 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.75 |
| Results tracked | 15 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 3 leads
DeepSeek LLM 67B: 31.9 (#278), Mistral Large 3: 34.4 (#237)
| Benchmark | DeepSeek LLM 67B | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1096 | 1448 |
| LMArena WebDev | — | 1230 |
Reasoning DeepSeek LLM 67B leads
DeepSeek LLM 67B: 16.5 (#304), Mistral Large 3: 15.2 (#319)
| Benchmark | DeepSeek LLM 67B | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 23% |
| Epoch Capabilities Index | 110.5 | — |
Math Mistral Large 3 leads
DeepSeek LLM 67B: 8.7 (#324), Mistral Large 3: 38.7 (#129)
| Benchmark | DeepSeek LLM 67B | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1108 | 1414 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Mistral Large 3 leads
DeepSeek LLM 67B: 7.0 (#313), Mistral Large 3: 36.0 (#177)
| Benchmark | DeepSeek LLM 67B | Mistral Large 3 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| Vectara Hallucination Rate | — | 14.5% |
| LMArena Expert | — | 1421 |
Multimodal Not comparable
DeepSeek LLM 67B: —, Mistral Large 3: 38.2 (#66)
| Benchmark | DeepSeek LLM 67B | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Mistral Large 3 leads
DeepSeek LLM 67B: 29.4 (#267), Mistral Large 3: 52.5 (#84)
| Benchmark | DeepSeek LLM 67B | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1073 | 1413 |
| LMArena Chinese | 1132 | 1447 |
| LMArena French | — | 1455 |
| LMArena German | — | 1437 |
| LMArena Japanese | — | 1394 |
| LMArena Korean | — | 1384 |
| LMArena Russian | — | 1411 |
| LMArena Spanish | — | 1440 |
Instruction Following Mistral Large 3 leads
DeepSeek LLM 67B: 55.4 (#277), Mistral Large 3: 74.0 (#108)
| Benchmark | DeepSeek LLM 67B | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1403 |
Long Context Mistral Large 3 leads
DeepSeek LLM 67B: 33.1 (#265), Mistral Large 3: 43.1 (#105)
| Benchmark | DeepSeek LLM 67B | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1092 | 1413 |
Writing & Preference Mistral Large 3 leads
DeepSeek LLM 67B: 31.6 (#282), Mistral Large 3: 60.0 (#101)
| Benchmark | DeepSeek LLM 67B | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1105 | 1428 |
| LMArena Creative Writing | 1067 | 1386 |
| LMArena Multi-Turn | 1082 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |
Frequently asked questions
Is DeepSeek LLM 67B better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Mistral Large 3 better for coding?
Mistral Large 3 scores higher on coding benchmarks: 34.4 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Mistral Large 3 share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Mistral Large 3 has 24.