Model comparison
DeepSeek Coder 33B vs Llama 2-70B
Llama 2-70B has enough public results to be ranked (#349); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Last verified . 5 shared benchmarks.
DeepSeek
MetaSummary
- They share 5 benchmarks with published results for both. DeepSeek Coder 33B scores higher in 1 category and Llama 2-70B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 33B leads 38.0 to 31.4.
Side by side
| DeepSeek Coder 33B | Llama 2-70B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 38.9 | 24.4 |
| Released | 2023-11-02 | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek Coder 33B leads
DeepSeek Coder 33B: 38.0 (#184), Llama 2-70B: 31.4 (#286)
| Benchmark | DeepSeek Coder 33B | Llama 2-70B |
|---|---|---|
| BigCodeBench Instruct | 42% | — |
| LMArena Coding | — | 1079 |
| BigCodeBench Complete | 51.1% | — |
| HumanEval+ | 75% | — |
| MBPP+ | 70.1% | — |
Reasoning Not comparable
DeepSeek Coder 33B: —, Llama 2-70B: 14.4 (#325)
| Benchmark | DeepSeek Coder 33B | Llama 2-70B |
|---|---|---|
| Epoch Capabilities Index | 96.32 | 113.79 |
| WinoGrande | 62% | 80.2% |
| LMArena Hard Prompts | — | 1073 |
| DTBench | — | 41.6% |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
Math Not comparable
DeepSeek Coder 33B: —, Llama 2-70B: 8.1 (#326)
| Benchmark | DeepSeek Coder 33B | Llama 2-70B |
|---|---|---|
| GSM8K | 35.4% | 69.6% |
| OTIS Mock AIME 2024-2025 | — | 0% |
| LMArena Math | — | 1091 |
| MATH Level 5 | — | 3.3% |
Knowledge Not comparable
DeepSeek Coder 33B: —, Llama 2-70B: 7.4 (#310)
| Benchmark | DeepSeek Coder 33B | Llama 2-70B |
|---|---|---|
| ARC (AI2) Challenge | 42.2% | 78.3% |
| MMLU | 39.4% | 69.9% |
| GPQA Diamond | — | 26.3% |
| LMArena Expert | — | 1039 |
| BoolQ | — | 88.6% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multilingual Not comparable
DeepSeek Coder 33B: —, Llama 2-70B: 27.7 (#274)
| Benchmark | DeepSeek Coder 33B | Llama 2-70B |
|---|---|---|
| LMArena Non-English | — | 1045 |
| LMArena Chinese | — | 995 |
| LMArena French | — | 1090 |
| LMArena German | — | 1041 |
| LMArena Japanese | — | 927 |
| LMArena Korean | — | 964 |
| LMArena Russian | — | 1083 |
| LMArena Spanish | — | 1143 |
Instruction Following Not comparable
DeepSeek Coder 33B: —, Llama 2-70B: 54.9 (#278)
| Benchmark | DeepSeek Coder 33B | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | — | 1071 |
Long Context Not comparable
DeepSeek Coder 33B: —, Llama 2-70B: 32.3 (#270)
| Benchmark | DeepSeek Coder 33B | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | — | 1062 |
Writing & Preference Not comparable
DeepSeek Coder 33B: —, Llama 2-70B: 32.3 (#279)
| Benchmark | DeepSeek Coder 33B | Llama 2-70B |
|---|---|---|
| LMArena Text | — | 1115 |
| LMArena Creative Writing | — | 1075 |
| LMArena Multi-Turn | — | 1088 |
Frequently asked questions
Is DeepSeek Coder 33B better than Llama 2-70B?
Llama 2-70B has enough public results to be ranked (#349); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 33B or Llama 2-70B better for coding?
DeepSeek Coder 33B scores higher on coding benchmarks: 38.0 versus 31.4 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 33B and Llama 2-70B share?
5 benchmarks have published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Llama 2-70B has 35.