Model comparison
DeepSeek-R1-Distill-Llama-70B vs Devstral Small 2505
DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 34.3 on the Noometry Index.
Last verified . 1 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 1 benchmark with published results for both. DeepSeek-R1-Distill-Llama-70B scores higher in 1 category and Devstral Small 2505 in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-R1-Distill-Llama-70B leads 24.9 to 19.7.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 52.3% for DeepSeek-R1-Distill-Llama-70B and 37.7% for Devstral Small 2505.
Side by side
| DeepSeek-R1-Distill-Llama-70B | Devstral Small 2505 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 37.8 | 34.3 |
| Released | 2025-01-20 | 2025-05-07 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 13 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Devstral Small 2505 leads
DeepSeek-R1-Distill-Llama-70B: 36.8 (#202), Devstral Small 2505: 38.9 (#166)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Devstral Small 2505 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 56.4% |
| SciCode | — | 28.8% |
| BigCodeBench Instruct | 35.3% | — |
| LiveBench Coding | 51.6% | — |
| BigCodeBench Complete | 49.9% | — |
Reasoning DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 24.9 (#156), Devstral Small 2505: 19.7 (#252)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Devstral Small 2505 |
|---|---|---|
| Kagi LLM Benchmark | 52.3% | 37.7% |
| CritPt | — | 0% |
| LiveBench Reasoning | 67.6% | — |
| LiveBench Data Analysis | 55.9% | — |
| LiveBench | 54.5% | — |
Math Not comparable
DeepSeek-R1-Distill-Llama-70B: 36.0 (#176), Devstral Small 2505: —
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Devstral Small 2505 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 51.4% | — |
| LiveBench Math | 58.1% | — |
| MATH Level 5 | 89.9% | — |
Knowledge Not comparable
DeepSeek-R1-Distill-Llama-70B: 30.7 (#225), Devstral Small 2505: —
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Devstral Small 2505 |
|---|---|---|
| GPQA Diamond | 55.7% | — |
Instruction Following Not comparable
DeepSeek-R1-Distill-Llama-70B: 68.2 (#190), Devstral Small 2505: —
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Devstral Small 2505 |
|---|---|---|
| LiveBench Instruction Following | 69.9% | — |
Writing & Preference Not comparable
DeepSeek-R1-Distill-Llama-70B: 49.0 (#194), Devstral Small 2505: —
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Devstral Small 2505 |
|---|---|---|
| LiveBench Language | 23.8% | — |
Frequently asked questions
Is DeepSeek-R1-Distill-Llama-70B better than Devstral Small 2505?
DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 34.3 on the Noometry Index.
Is DeepSeek-R1-Distill-Llama-70B or Devstral Small 2505 better for coding?
Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 36.8 in the Noometry coding category.
How many benchmarks do DeepSeek-R1-Distill-Llama-70B and Devstral Small 2505 share?
1 benchmark has published results for both models. DeepSeek-R1-Distill-Llama-70B has 13 scored results on Noometry and Devstral Small 2505 has 4.