Model comparison
DeepSeek Coder 33B vs Llama 2-13B
Llama 2-13B has enough public results to be ranked (#304); 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 2-13B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 33B leads 37.4 to 30.4.
Side by side
| DeepSeek Coder 33B | Llama 2-13B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 38.3 | 29.1 |
| Released | 2023-11-02 | 2023-07-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek Coder 33B leads
DeepSeek Coder 33B: 37.4 (#180), Llama 2-13B: 30.4 (#287)
| Benchmark | DeepSeek Coder 33B | Llama 2-13B |
|---|---|---|
| BigCodeBench Instruct | 42% | — |
| LMArena Coding | — | 1062 |
| BigCodeBench Complete | 51.1% | — |
| HumanEval+ | 75% | — |
| MBPP+ | 70.1% | — |
Reasoning Not comparable
DeepSeek Coder 33B: —, Llama 2-13B: 12.3 (#333)
| Benchmark | DeepSeek Coder 33B | Llama 2-13B |
|---|---|---|
| Epoch Capabilities Index | 95.74 | 105.8 |
| WinoGrande | 62% | 72.8% |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1051 |
| DTBench | — | 42.2% |
| BIG-Bench Hard | — | 58.2% |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
Math Not comparable
DeepSeek Coder 33B: —, Llama 2-13B: 28.7 (#226)
| Benchmark | DeepSeek Coder 33B | Llama 2-13B |
|---|---|---|
| GSM8K | 35.4% | 36.9% |
| LMArena Math | — | 1065 |
Knowledge Not comparable
DeepSeek Coder 33B: —, Llama 2-13B: 27.5 (#244)
| Benchmark | DeepSeek Coder 33B | Llama 2-13B |
|---|---|---|
| ARC (AI2) Challenge | 42.2% | 60.3% |
| MMLU | 39.4% | 55.6% |
| LMArena Expert | — | 1030 |
| BoolQ | — | 82.4% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
DeepSeek Coder 33B: —, Llama 2-13B: —
| Benchmark | DeepSeek Coder 33B | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual Not comparable
DeepSeek Coder 33B: —, Llama 2-13B: 26.7 (#274)
| Benchmark | DeepSeek Coder 33B | Llama 2-13B |
|---|---|---|
| LMArena Non-English | — | 1024 |
| LMArena Chinese | — | 1001 |
| LMArena French | — | 1043 |
| LMArena German | — | 1009 |
| LMArena Japanese | — | 894 |
| LMArena Korean | — | 953 |
| LMArena Russian | — | 1055 |
| LMArena Spanish | — | 1086 |
Instruction Following Not comparable
DeepSeek Coder 33B: —, Llama 2-13B: 53.5 (#282)
| Benchmark | DeepSeek Coder 33B | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | — | 1046 |
Long Context Not comparable
DeepSeek Coder 33B: —, Llama 2-13B: 32.3 (#264)
| Benchmark | DeepSeek Coder 33B | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | — | 1064 |
Writing & Preference Not comparable
DeepSeek Coder 33B: —, Llama 2-13B: 30.0 (#284)
| Benchmark | DeepSeek Coder 33B | Llama 2-13B |
|---|---|---|
| LMArena Text | — | 1085 |
| LMArena Creative Writing | — | 1047 |
| LMArena Multi-Turn | — | 1050 |
Frequently asked questions
Is DeepSeek Coder 33B better than Llama 2-13B?
Llama 2-13B has enough public results to be ranked (#304); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 33B or Llama 2-13B better for coding?
DeepSeek Coder 33B scores higher on coding benchmarks: 37.4 versus 30.4 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 33B and Llama 2-13B share?
5 benchmarks have published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Llama 2-13B has 32.