Model comparison
DeepSeek LLM 67B vs Llama 2-13B
Llama 2-13B is the stronger model overall, scoring 29.6 to 24.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
MetaSummary
- They share 12 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 6 categories and Llama 2-13B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 2-13B leads 31.1 to 8.7.
Side by side
| DeepSeek LLM 67B | Llama 2-13B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 24.9 | 29.6 |
| Released | 2023-11-29 | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 32 |
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 2-13B: 30.9 (#291)
| Benchmark | DeepSeek LLM 67B | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1096 | 1062 |
Reasoning DeepSeek LLM 67B leads
DeepSeek LLM 67B: 16.5 (#304), Llama 2-13B: 12.8 (#337)
| Benchmark | DeepSeek LLM 67B | Llama 2-13B |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1070 | 1051 |
| Epoch Capabilities Index | 110.5 | 106.17 |
| DTBench | — | 42.2% |
| BIG-Bench Hard | — | 58.2% |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Llama 2-13B leads
DeepSeek LLM 67B: 8.7 (#324), Llama 2-13B: 31.1 (#229)
| Benchmark | DeepSeek LLM 67B | Llama 2-13B |
|---|---|---|
| LMArena Math | 1108 | 1065 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
| GSM8K | — | 36.9% |
Knowledge Llama 2-13B leads
DeepSeek LLM 67B: 7.0 (#313), Llama 2-13B: 28.1 (#249)
| Benchmark | DeepSeek LLM 67B | Llama 2-13B |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1030 |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
DeepSeek LLM 67B: —, Llama 2-13B: —
| Benchmark | DeepSeek LLM 67B | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual DeepSeek LLM 67B leads
DeepSeek LLM 67B: 29.4 (#267), Llama 2-13B: 26.5 (#279)
| Benchmark | DeepSeek LLM 67B | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1073 | 1024 |
| LMArena Chinese | 1132 | 1001 |
| LMArena French | — | 1044 |
| LMArena German | — | 1009 |
| LMArena Japanese | — | 894 |
| LMArena Korean | — | 953 |
| LMArena Russian | — | 1055 |
| LMArena Spanish | — | 1087 |
Instruction Following DeepSeek LLM 67B leads
DeepSeek LLM 67B: 55.4 (#277), Llama 2-13B: 53.3 (#287)
| Benchmark | DeepSeek LLM 67B | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1045 |
Long Context Too close to call
DeepSeek LLM 67B: 33.1 (#265), Llama 2-13B: 32.3 (#269)
| Benchmark | DeepSeek LLM 67B | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1092 | 1064 |
Writing & Preference DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.6 (#282), Llama 2-13B: 29.8 (#289)
| Benchmark | DeepSeek LLM 67B | Llama 2-13B |
|---|---|---|
| LMArena Text | 1105 | 1084 |
| LMArena Creative Writing | 1067 | 1047 |
| LMArena Multi-Turn | 1082 | 1050 |
Frequently asked questions
Is DeepSeek LLM 67B better than Llama 2-13B?
Llama 2-13B is the stronger model overall, scoring 29.6 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Llama 2-13B better for coding?
They score almost the same on coding (31.9 vs 30.9); test both on your own repository before choosing.
How many benchmarks do DeepSeek LLM 67B and Llama 2-13B share?
12 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Llama 2-13B has 32.