Model comparison
DeepSeek-R1-Distill-Llama-70B vs Mistral Small
DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 33.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 13 benchmarks with published results for both. DeepSeek-R1-Distill-Llama-70B scores higher in 4 categories and Mistral Small in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-R1-Distill-Llama-70B leads 36.0 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 51.4% for DeepSeek-R1-Distill-Llama-70B and 5.8% for Mistral Small.
Side by side
| DeepSeek-R1-Distill-Llama-70B | Mistral Small | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 37.8 | 33.4 |
| Released | 2025-01-20 | 2024-02-26 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 13 | 39 |
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 Small: 34.0 (#247)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral Small |
|---|---|---|
| BigCodeBench Instruct | 35.3% | 36.1% |
| LiveBench Coding | 51.6% | 36.2% |
| BigCodeBench Complete | 49.9% | 46.6% |
| SciCode | — | 26.5% |
| LMArena Coding | — | 1362 |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Not comparable
DeepSeek-R1-Distill-Llama-70B: —, Mistral Small: 28.1 (#93)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 24.9 (#156), Mistral Small: 19.8 (#250)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 52.3% | 37.8% |
| LiveBench Reasoning | 67.6% | 44.8% |
| LiveBench Data Analysis | 55.9% | 53.7% |
| LiveBench | 54.5% | 44% |
| CritPt | — | 0% |
| LMArena Hard Prompts | — | 1335 |
| DTBench | — | 70.9% |
| LMCA | — | 20.6% |
Math DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 36.0 (#176), Mistral Small: 16.4 (#293)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 51.4% | 5.8% |
| LiveBench Math | 58.1% | 39.9% |
| MATH Level 5 | 89.9% | 46.8% |
| LMArena Math | — | 1341 |
Knowledge Too close to call
DeepSeek-R1-Distill-Llama-70B: 30.7 (#225), Mistral Small: 31.0 (#222)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral Small |
|---|---|---|
| GPQA Diamond | 55.7% | 47.5% |
| Vectara Hallucination Rate | — | 5.1% |
| LMArena Expert | — | 1291 |
| MMLU | — | 68.7% |
Multimodal Not comparable
DeepSeek-R1-Distill-Llama-70B: —, Mistral Small: 33.5 (#96)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Not comparable
DeepSeek-R1-Distill-Llama-70B: —, Mistral Small: 45.5 (#169)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral Small |
|---|---|---|
| LMArena Non-English | — | 1315 |
| LMArena Chinese | — | 1340 |
| LMArena French | — | 1337 |
| LMArena German | — | 1340 |
| LMArena Japanese | — | 1275 |
| LMArena Korean | — | 1259 |
| LMArena Russian | — | 1324 |
| LMArena Spanish | — | 1346 |
Instruction Following DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 68.2 (#190), Mistral Small: 66.4 (#209)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral Small |
|---|---|---|
| LiveBench Instruction Following | 69.9% | 63.7% |
| LMArena Instruction Following | — | 1310 |
Long Context Not comparable
DeepSeek-R1-Distill-Llama-70B: —, Mistral Small: 40.4 (#156)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral Small |
|---|---|---|
| LMArena Longer Query | — | 1327 |
Writing & Preference Mistral Small leads
DeepSeek-R1-Distill-Llama-70B: 49.0 (#194), Mistral Small: 52.5 (#171)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Mistral Small |
|---|---|---|
| LiveBench Language | 23.8% | 30.5% |
| LMArena Text | — | 1338 |
| LMArena Creative Writing | — | 1305 |
| LMArena Multi-Turn | — | 1344 |
Frequently asked questions
Is DeepSeek-R1-Distill-Llama-70B better than Mistral Small?
DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 33.4 on the Noometry Index.
Is DeepSeek-R1-Distill-Llama-70B or Mistral Small better for coding?
DeepSeek-R1-Distill-Llama-70B scores higher on coding benchmarks: 36.8 versus 34.0 in the Noometry coding category.
How many benchmarks do DeepSeek-R1-Distill-Llama-70B and Mistral Small share?
13 benchmarks have published results for both models. DeepSeek-R1-Distill-Llama-70B has 13 scored results on Noometry and Mistral Small has 39.