Model comparison
DeepSeek LLM 67B vs Llama 2-70B
DeepSeek LLM 67B and Llama 2-70B score almost the same on the Noometry Index (24.9 vs 24.4), so choose on price, context window or the category you care about most.
Last verified . 14 shared benchmarks.
DeepSeek
MetaSummary
- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 6 categories and Llama 2-70B in 2 categories; 2 gaps are clear of the uncertainty.
Side by side
| DeepSeek LLM 67B | Llama 2-70B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 24.9 | 24.4 |
| Released | 2023-11-29 | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek LLM 67B: 31.9 (#278), Llama 2-70B: 31.4 (#286)
| Benchmark | DeepSeek LLM 67B | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1096 | 1079 |
Reasoning DeepSeek LLM 67B leads
DeepSeek LLM 67B: 16.5 (#304), Llama 2-70B: 14.4 (#325)
| Benchmark | DeepSeek LLM 67B | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1073 |
| Epoch Capabilities Index | 110.5 | 113.79 |
| Chess Puzzles | 0% | — |
| DTBench | — | 41.6% |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math Too close to call
DeepSeek LLM 67B: 8.7 (#324), Llama 2-70B: 8.1 (#326)
| Benchmark | DeepSeek LLM 67B | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 0% |
| LMArena Math | 1108 | 1091 |
| MATH Level 5 | 6.4% | 3.3% |
| GSM8K | — | 69.6% |
Knowledge Too close to call
DeepSeek LLM 67B: 7.0 (#313), Llama 2-70B: 7.4 (#310)
| Benchmark | DeepSeek LLM 67B | Llama 2-70B |
|---|---|---|
| GPQA Diamond | 24.6% | 26.3% |
| LMArena Expert | — | 1039 |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multilingual DeepSeek LLM 67B leads
DeepSeek LLM 67B: 29.4 (#267), Llama 2-70B: 27.7 (#274)
| Benchmark | DeepSeek LLM 67B | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1073 | 1045 |
| LMArena Chinese | 1132 | 995 |
| LMArena French | — | 1090 |
| LMArena German | — | 1041 |
| LMArena Japanese | — | 927 |
| LMArena Korean | — | 964 |
| LMArena Russian | — | 1083 |
| LMArena Spanish | — | 1143 |
Instruction Following Too close to call
DeepSeek LLM 67B: 55.4 (#277), Llama 2-70B: 54.9 (#278)
| Benchmark | DeepSeek LLM 67B | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1071 |
Long Context Too close to call
DeepSeek LLM 67B: 33.1 (#265), Llama 2-70B: 32.3 (#270)
| Benchmark | DeepSeek LLM 67B | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1092 | 1062 |
Writing & Preference Too close to call
DeepSeek LLM 67B: 31.6 (#282), Llama 2-70B: 32.3 (#279)
| Benchmark | DeepSeek LLM 67B | Llama 2-70B |
|---|---|---|
| LMArena Text | 1105 | 1115 |
| LMArena Creative Writing | 1067 | 1075 |
| LMArena Multi-Turn | 1082 | 1088 |
Frequently asked questions
Is DeepSeek LLM 67B better than Llama 2-70B?
DeepSeek LLM 67B and Llama 2-70B score almost the same on the Noometry Index (24.9 vs 24.4), so choose on price, context window or the category you care about most.
Is DeepSeek LLM 67B or Llama 2-70B better for coding?
They score almost the same on coding (31.9 vs 31.4); test both on your own repository before choosing.
How many benchmarks do DeepSeek LLM 67B and Llama 2-70B share?
14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Llama 2-70B has 35.