Model comparison
DeepSeek LLM 67B vs Mistral 7B
DeepSeek LLM 67B is the stronger model overall, scoring 24.9 to 23.0 on the Noometry Index.
Last verified . 15 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 15 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 7 categories and Mistral 7B in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek LLM 67B leads 31.9 to 26.4.
- The biggest single-benchmark swing is GPQA Diamond: 24.6% for DeepSeek LLM 67B and 15.2% for Mistral 7B.
Side by side
| DeepSeek LLM 67B | Mistral 7B | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 24.9 | 23.0 |
| Released | 2023-11-29 | 2023-09-27 |
| Weights | Open | Open |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.25 |
| Results tracked | 15 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.9 (#278), Mistral 7B: 26.4 (#326)
| Benchmark | DeepSeek LLM 67B | Mistral 7B |
|---|---|---|
| LMArena Coding | 1096 | 1082 |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Reasoning DeepSeek LLM 67B leads
DeepSeek LLM 67B: 16.5 (#304), Mistral 7B: 13.1 (#336)
| Benchmark | DeepSeek LLM 67B | Mistral 7B |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1070 | 1067 |
| Epoch Capabilities Index | 110.5 | 112.21 |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math Too close to call
DeepSeek LLM 67B: 8.7 (#324), Mistral 7B: 8.1 (#325)
| Benchmark | DeepSeek LLM 67B | Mistral 7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 0.3% |
| LMArena Math | 1108 | 1085 |
| MATH Level 5 | 6.4% | 3.7% |
| GSM8K | — | 54.4% |
Knowledge Too close to call
DeepSeek LLM 67B: 7.0 (#313), Mistral 7B: 7.4 (#311)
| Benchmark | DeepSeek LLM 67B | Mistral 7B |
|---|---|---|
| GPQA Diamond | 24.6% | 15.2% |
| LMArena Expert | — | 1036 |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multilingual DeepSeek LLM 67B leads
DeepSeek LLM 67B: 29.4 (#267), Mistral 7B: 25.8 (#283)
| Benchmark | DeepSeek LLM 67B | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1073 | 1012 |
| LMArena Chinese | 1132 | 1009 |
| LMArena French | — | 1037 |
| LMArena German | — | 987 |
| LMArena Japanese | — | 878 |
| LMArena Russian | — | 1018 |
| LMArena Spanish | — | 1026 |
Instruction Following DeepSeek LLM 67B leads
DeepSeek LLM 67B: 55.4 (#277), Mistral 7B: 54.2 (#280)
| Benchmark | DeepSeek LLM 67B | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1060 |
Long Context Too close to call
DeepSeek LLM 67B: 33.1 (#265), Mistral 7B: 32.2 (#271)
| Benchmark | DeepSeek LLM 67B | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1092 | 1060 |
Writing & Preference Too close to call
DeepSeek LLM 67B: 31.6 (#282), Mistral 7B: 30.7 (#286)
| Benchmark | DeepSeek LLM 67B | Mistral 7B |
|---|---|---|
| LMArena Text | 1105 | 1090 |
| LMArena Creative Writing | 1067 | 1068 |
| LMArena Multi-Turn | 1082 | 1062 |
Frequently asked questions
Is DeepSeek LLM 67B better than Mistral 7B?
DeepSeek LLM 67B is the stronger model overall, scoring 24.9 to 23.0 on the Noometry Index.
Is DeepSeek LLM 67B or Mistral 7B better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 26.4 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Mistral 7B share?
15 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Mistral 7B has 37.