Model comparison
DeepSeek Coder 1.3B vs Llama 2-34B
Neither DeepSeek Coder 1.3B nor Llama 2-34B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 5 shared benchmarks.
DeepSeek
MetaSummary
- They share 5 benchmarks with published results for both.
- DeepSeek Coder 1.3B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek Coder 1.3B | Llama 2-34B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 35.0 | — |
| Released | 2023-11-02 | 2023-07-18 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek Coder 1.3B: 31.2 (#287), Llama 2-34B: —
| Benchmark | DeepSeek Coder 1.3B | Llama 2-34B |
|---|---|---|
| BigCodeBench Instruct | 22.8% | — |
| BigCodeBench Complete | 29.6% | — |
| HumanEval+ | 60.4% | — |
| MBPP+ | 54.8% | — |
Reasoning Not comparable
DeepSeek Coder 1.3B: —, Llama 2-34B: —
| Benchmark | DeepSeek Coder 1.3B | Llama 2-34B |
|---|---|---|
| Epoch Capabilities Index | 63.6 | 105.2 |
| WinoGrande | 53.3% | 76.7% |
| BIG-Bench Hard | — | 44.1% |
| PIQA | — | 81.9% |
Math Not comparable
DeepSeek Coder 1.3B: —, Llama 2-34B: —
| Benchmark | DeepSeek Coder 1.3B | Llama 2-34B |
|---|---|---|
| GSM8K | 4.4% | 42.2% |
Knowledge Not comparable
DeepSeek Coder 1.3B: —, Llama 2-34B: —
| Benchmark | DeepSeek Coder 1.3B | Llama 2-34B |
|---|---|---|
| ARC (AI2) Challenge | 25.4% | 54.5% |
| MMLU | 25.8% | 62.6% |
| BoolQ | — | 83.7% |
| OpenBookQA | — | 58.2% |
| TriviaQA | — | 84.6% |
Frequently asked questions
Is DeepSeek Coder 1.3B better than Llama 2-34B?
Neither DeepSeek Coder 1.3B nor Llama 2-34B has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do DeepSeek Coder 1.3B and Llama 2-34B share?
5 benchmarks have published results for both models. DeepSeek Coder 1.3B has 9 scored results on Noometry and Llama 2-34B has 10.