Model comparison
DeepSeek-R1-Distill-Llama-70B vs Gemma 2B
DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 29.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
GoogleSummary
- The widest gap is in writing & preference, where DeepSeek-R1-Distill-Llama-70B leads 49.0 to 24.0.
Side by side
| DeepSeek-R1-Distill-Llama-70B | Gemma 2B | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 37.8 | 29.6 |
| Released | 2025-01-20 | 2024-02-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 23 |
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), Gemma 2B: 29.4 (#305)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Gemma 2B |
|---|---|---|
| BigCodeBench Instruct | 35.3% | — |
| LiveBench Coding | 51.6% | — |
| LMArena Coding | — | 1010 |
| BigCodeBench Complete | 49.9% | — |
| HumanEval+ | — | 20.7% |
| MBPP+ | — | 34.1% |
Reasoning DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 24.9 (#156), Gemma 2B: 18.8 (#275)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Gemma 2B |
|---|---|---|
| Kagi LLM Benchmark | 52.3% | — |
| LiveBench Reasoning | 67.6% | — |
| LMArena Hard Prompts | — | 989 |
| LiveBench Data Analysis | 55.9% | — |
| BIG-Bench Hard | — | 35.2% |
| Epoch Capabilities Index | — | 94.2 |
| HellaSwag | — | 71.4% |
| LiveBench | 54.5% | — |
| PIQA | — | 77.3% |
| WinoGrande | — | 65.4% |
Math DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 36.0 (#176), Gemma 2B: 30.0 (#239)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Gemma 2B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 51.4% | — |
| LiveBench Math | 58.1% | — |
| LMArena Math | — | 1009 |
| MATH Level 5 | 89.9% | — |
| GSM8K | — | 17.7% |
Knowledge Not comparable
DeepSeek-R1-Distill-Llama-70B: 30.7 (#225), Gemma 2B: —
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Gemma 2B |
|---|---|---|
| GPQA Diamond | 55.7% | — |
| ARC (AI2) Challenge | — | 42.1% |
| BoolQ | — | 69.4% |
| MMLU | — | 42.3% |
| TriviaQA | — | 53.2% |
Multilingual Not comparable
DeepSeek-R1-Distill-Llama-70B: —, Gemma 2B: 23.0 (#294)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Gemma 2B |
|---|---|---|
| LMArena Non-English | — | 958 |
| LMArena Chinese | — | 986 |
| LMArena Russian | — | 937 |
Instruction Following DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 68.2 (#190), Gemma 2B: 48.5 (#302)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Gemma 2B |
|---|---|---|
| LiveBench Instruction Following | 69.9% | — |
| LMArena Instruction Following | — | 970 |
Long Context Not comparable
DeepSeek-R1-Distill-Llama-70B: —, Gemma 2B: 29.9 (#291)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Gemma 2B |
|---|---|---|
| LMArena Longer Query | — | 981 |
Writing & Preference DeepSeek-R1-Distill-Llama-70B leads
DeepSeek-R1-Distill-Llama-70B: 49.0 (#194), Gemma 2B: 24.0 (#308)
| Benchmark | DeepSeek-R1-Distill-Llama-70B | Gemma 2B |
|---|---|---|
| LMArena Text | — | 1002 |
| LMArena Creative Writing | — | 987 |
| LMArena Multi-Turn | — | 945 |
| LiveBench Language | 23.8% | — |
Frequently asked questions
Is DeepSeek-R1-Distill-Llama-70B better than Gemma 2B?
DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.8 to 29.6 on the Noometry Index.
Is DeepSeek-R1-Distill-Llama-70B or Gemma 2B better for coding?
DeepSeek-R1-Distill-Llama-70B scores higher on coding benchmarks: 36.8 versus 29.4 in the Noometry coding category.
How many benchmarks do DeepSeek-R1-Distill-Llama-70B and Gemma 2B share?
0 benchmarks have published results for both models. DeepSeek-R1-Distill-Llama-70B has 13 scored results on Noometry and Gemma 2B has 23.