Model comparison
DeepSeek LLM 67B vs Llama 3-70B
Llama 3-70B is the stronger model overall, scoring 28.5 to 24.8 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeek
MetaSummary
- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Llama 3-70B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3-70B leads 20.8 to 7.1.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 22.6% for Llama 3-70B.
Side by side
| DeepSeek LLM 67B | Llama 3-70B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 24.8 | 28.5 |
| Released | 2023-11-29 | 2024-04-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
DeepSeek LLM 67B: 31.3 (#273), Llama 3-70B: 35.3 (#215)
| Benchmark | DeepSeek LLM 67B | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1096 | 1206 |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Llama 3-70B: 20.9 (#132)
| Benchmark | DeepSeek LLM 67B | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning Llama 3-70B leads
DeepSeek LLM 67B: 15.9 (#300), Llama 3-70B: 17.4 (#284)
| Benchmark | DeepSeek LLM 67B | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1195 |
| Epoch Capabilities Index | 110.54 | 122.91 |
| Kagi LLM Benchmark | — | 35.1% |
| Chess Puzzles | 0% | — |
| DTBench | — | 54.2% |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math Llama 3-70B leads
DeepSeek LLM 67B: 8.1 (#318), Llama 3-70B: 12.0 (#299)
| Benchmark | DeepSeek LLM 67B | Llama 3-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 4.3% |
| LMArena Math | 1108 | 1218 |
| MATH Level 5 | 6.4% | 22.6% |
Knowledge Llama 3-70B leads
DeepSeek LLM 67B: 7.1 (#308), Llama 3-70B: 20.8 (#272)
| Benchmark | DeepSeek LLM 67B | Llama 3-70B |
|---|---|---|
| GPQA Diamond | 24.6% | 40.6% |
| LMArena Expert | — | 1149 |
| MMLU | — | 79.3% |
Multilingual Llama 3-70B leads
DeepSeek LLM 67B: 29.5 (#262), Llama 3-70B: 33.8 (#246)
| Benchmark | DeepSeek LLM 67B | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1073 | 1142 |
| LMArena Chinese | 1132 | 1114 |
| LMArena French | — | 1231 |
| LMArena German | — | 1169 |
| LMArena Japanese | — | 1017 |
| LMArena Korean | — | 1017 |
| LMArena Russian | — | 1159 |
| LMArena Spanish | — | 1241 |
Instruction Following Llama 3-70B leads
DeepSeek LLM 67B: 55.7 (#272), Llama 3-70B: 62.8 (#233)
| Benchmark | DeepSeek LLM 67B | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1194 |
Long Context Llama 3-70B leads
DeepSeek LLM 67B: 33.1 (#260), Llama 3-70B: 35.6 (#235)
| Benchmark | DeepSeek LLM 67B | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1092 | 1174 |
Writing & Preference Llama 3-70B leads
DeepSeek LLM 67B: 31.8 (#277), Llama 3-70B: 43.0 (#225)
| Benchmark | DeepSeek LLM 67B | Llama 3-70B |
|---|---|---|
| LMArena Text | 1105 | 1221 |
| LMArena Creative Writing | 1067 | 1210 |
| LMArena Multi-Turn | 1082 | 1223 |
Frequently asked questions
Is DeepSeek LLM 67B better than Llama 3-70B?
Llama 3-70B is the stronger model overall, scoring 28.5 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.3 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Llama 3-70B share?
14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Llama 3-70B has 31.