Model comparison
DeepSeek LLM 67B vs Llama 13b
DeepSeek LLM 67B and Llama 13b 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 . 9 shared benchmarks.
DeepSeek
MetaSummary
- They share 9 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 5 categories and Llama 13b in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where DeepSeek LLM 67B leads 55.4 to 36.7.
Side by side
| DeepSeek LLM 67B | Llama 13b | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 24.9 | 24.4 |
| Released | 2023-11-29 | 2023-02-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.9 (#278), Llama 13b: 21.4 (#337)
| Benchmark | DeepSeek LLM 67B | Llama 13b |
|---|---|---|
| LMArena Coding | 1096 | 683 |
Reasoning DeepSeek LLM 67B leads
DeepSeek LLM 67B: 16.5 (#304), Llama 13b: 14.0 (#329)
| Benchmark | DeepSeek LLM 67B | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1070 | 728 |
| Epoch Capabilities Index | 110.5 | 100.58 |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | — | 37.9% |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math Llama 13b leads
DeepSeek LLM 67B: 8.7 (#324), Llama 13b: 26.7 (#256)
| Benchmark | DeepSeek LLM 67B | Llama 13b |
|---|---|---|
| LMArena Math | 1108 | 838 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
| GSM8K | — | 20.6% |
Knowledge Not comparable
DeepSeek LLM 67B: 7.0 (#313), Llama 13b: —
| Benchmark | DeepSeek LLM 67B | Llama 13b |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
DeepSeek LLM 67B: —, Llama 13b: —
| Benchmark | DeepSeek LLM 67B | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual DeepSeek LLM 67B leads
DeepSeek LLM 67B: 29.4 (#267), Llama 13b: 16.6 (#297)
| Benchmark | DeepSeek LLM 67B | Llama 13b |
|---|---|---|
| LMArena Non-English | 1073 | 819 |
| LMArena Chinese | 1132 | — |
Instruction Following DeepSeek LLM 67B leads
DeepSeek LLM 67B: 55.4 (#277), Llama 13b: 36.7 (#305)
| Benchmark | DeepSeek LLM 67B | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1079 | 781 |
Long Context Not comparable
DeepSeek LLM 67B: 33.1 (#265), Llama 13b: —
| Benchmark | DeepSeek LLM 67B | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1092 | — |
Writing & Preference DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.6 (#282), Llama 13b: 13.8 (#312)
| Benchmark | DeepSeek LLM 67B | Llama 13b |
|---|---|---|
| LMArena Text | 1105 | 834 |
| LMArena Creative Writing | 1067 | 794 |
| LMArena Multi-Turn | 1082 | 753 |
Frequently asked questions
Is DeepSeek LLM 67B better than Llama 13b?
DeepSeek LLM 67B and Llama 13b 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 13b better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 21.4 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Llama 13b share?
9 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Llama 13b has 21.