Model comparison
DeepSeek-R1-Distill-Llama-70B vs Phi 3 Small 8k Instruct
DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 29.3 on the Noometry Index.
Last verified . 7 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 7 benchmarks with published results for both. DeepSeek-R1-Distill-Llama-70B scores higher in 6 categories and Phi 3 Small 8k Instruct in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-R1-Distill-Llama-70B leads 49.0 to 31.1.
- The biggest single-benchmark swing is LiveBench Reasoning: 67.6% for DeepSeek-R1-Distill-Llama-70B and 15.9% for Phi 3 Small 8k Instruct.
Side by side
| DeepSeek-R1-Distill-Llama-70B | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 37.8 | 29.3 |
| Released | 2025-01-20 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 32 |
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), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Coding | 51.6% | 20.3% |
| BigCodeBench Instruct | 35.3% | — |
| LMArena Coding | — | 1101 |
| BigCodeBench Complete | 49.9% | — |
Reasoning DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 24.9 (#156), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Reasoning | 67.6% | 15.9% |
| LiveBench Data Analysis | 55.9% | 30.3% |
| LiveBench | 54.5% | 24% |
| Kagi LLM Benchmark | 52.3% | — |
| LMArena Hard Prompts | — | 1100 |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| HellaSwag | — | 77% |
| WinoGrande | — | 81.5% |
Math DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 36.0 (#176), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Math | 58.1% | 17.6% |
| OTIS Mock AIME 2024-2025 | 51.4% | — |
| LMArena Math | — | 1151 |
| MATH Level 5 | 89.9% | — |
Knowledge DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 30.7 (#225), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| GPQA Diamond | 55.7% | — |
| LMArena Expert | — | 1067 |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multilingual Not comparable
DeepSeek-R1-Distill-Llama-70B: —, Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | — | 1058 |
| LMArena Chinese | — | 1061 |
| LMArena French | — | 1135 |
| LMArena German | — | 1080 |
| LMArena Japanese | — | 966 |
| LMArena Korean | — | 894 |
| LMArena Russian | — | 1111 |
| LMArena Spanish | — | 1111 |
Instruction Following DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 68.2 (#190), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Instruction Following | 69.9% | 47.2% |
| LMArena Instruction Following | — | 1087 |
Long Context Not comparable
DeepSeek-R1-Distill-Llama-70B: —, Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | — | 1088 |
Writing & Preference DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 49.0 (#194), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Language | 23.8% | 12.9% |
| LMArena Text | — | 1110 |
| LMArena Creative Writing | — | 1083 |
| LMArena Multi-Turn | — | 1068 |
Frequently asked questions
Is DeepSeek-R1-Distill-Llama-70B better than Phi 3 Small 8k Instruct?
DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 29.3 on the Noometry Index.
Is DeepSeek-R1-Distill-Llama-70B or Phi 3 Small 8k Instruct better for coding?
DeepSeek-R1-Distill-Llama-70B scores higher on coding benchmarks: 36.8 versus 27.9 in the Noometry coding category.
How many benchmarks do DeepSeek-R1-Distill-Llama-70B and Phi 3 Small 8k Instruct share?
7 benchmarks have published results for both models. DeepSeek-R1-Distill-Llama-70B has 13 scored results on Noometry and Phi 3 Small 8k Instruct has 32.