Model comparison
DeepSeek-R1-Distill-Llama-70B vs Mistral
DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 29.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
Mistral AISummary
- The widest gap is in instruction following, where DeepSeek-R1-Distill-Llama-70B leads 68.2 to 52.6.
- DeepSeek-R1-Distill-Llama-70B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-R1-Distill-Llama-70B | Mistral | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 37.8 | 29.9 |
| Released | 2025-01-20 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 36.8 (#202), Mistral: 33.8 (#250)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral |
|---|---|---|
| BigCodeBench Instruct | 35.3% | — |
| LiveBench Coding | 51.6% | — |
| LMArena Coding | — | 1162 |
| BigCodeBench Complete | 49.9% | — |
Reasoning DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 24.9 (#156), Mistral: 22.2 (#200)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral |
|---|---|---|
| Kagi LLM Benchmark | 52.3% | — |
| LiveBench Reasoning | 67.6% | — |
| LMArena Hard Prompts | — | 1149 |
| LiveBench Data Analysis | 55.9% | — |
| LiveBench | 54.5% | — |
Math DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 36.0 (#176), Mistral: 22.3 (#278)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 51.4% | — |
| Omni-MATH | — | 7.2% |
| LiveBench Math | 58.1% | — |
| LMArena Math | — | 1180 |
| MATH Level 5 | 89.9% | — |
Knowledge DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 30.7 (#225), Mistral: 16.6 (#288)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral |
|---|---|---|
| GPQA Diamond | 55.7% | — |
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| LMArena Expert | — | 1125 |
Multilingual Not comparable
DeepSeek-R1-Distill-Llama-70B: —, Mistral: 32.8 (#254)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral |
|---|---|---|
| LMArena Non-English | — | 1129 |
| LMArena Chinese | — | 1109 |
| LMArena French | — | 1180 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1013 |
| LMArena Korean | — | 1032 |
| LMArena Russian | — | 1168 |
| LMArena Spanish | — | 1143 |
Instruction Following DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 68.2 (#190), Mistral: 52.6 (#288)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral |
|---|---|---|
| LiveBench Instruction Following | 69.9% | — |
| IFEval | — | 56.8% |
| LMArena Instruction Following | — | 1152 |
Long Context Not comparable
DeepSeek-R1-Distill-Llama-70B: —, Mistral: 35.0 (#245)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral |
|---|---|---|
| LMArena Longer Query | — | 1153 |
Writing & Preference DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 49.0 (#194), Mistral: 37.0 (#260)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral |
|---|---|---|
| LMArena Text | — | 1165 |
| LMArena Creative Writing | — | 1158 |
| WildBench | — | 66% |
| LMArena Multi-Turn | — | 1147 |
| LiveBench Language | 23.8% | — |
Frequently asked questions
Is DeepSeek-R1-Distill-Llama-70B better than Mistral?
DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 29.9 on the Noometry Index.
Is DeepSeek-R1-Distill-Llama-70B or Mistral better for coding?
DeepSeek-R1-Distill-Llama-70B scores higher on coding benchmarks: 36.8 versus 33.8 in the Noometry coding category.
How many benchmarks do DeepSeek-R1-Distill-Llama-70B and Mistral share?
0 benchmarks have published results for both models. DeepSeek-R1-Distill-Llama-70B has 13 scored results on Noometry and Mistral has 22.