Model comparison
DeepSeek Coder 33B vs Deepseek Coder v2
Deepseek Coder v2 has enough public results to be ranked (#220); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Last verified . 7 shared benchmarks.
DeepSeekSummary
- They share 7 benchmarks with published results for both. DeepSeek Coder 33B scores higher in 0 categories and Deepseek Coder v2 in 1 category, but none of those gaps is larger than the uncertainty.
- The biggest single-benchmark swing is BigCodeBench Complete: 51.1% for DeepSeek Coder 33B and 59.7% for Deepseek Coder v2.
Side by side
| DeepSeek Coder 33B | Deepseek Coder v2 | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 38.9 | 35.9 |
| Released | 2023-11-02 | 2024-06-17 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek Coder 33B: 38.0 (#184), Deepseek Coder v2: 38.1 (#183)
| Benchmark | DeepSeek Coder 33B | Deepseek Coder v2 |
|---|---|---|
| BigCodeBench Instruct | 42% | 48.2% |
| BigCodeBench Complete | 51.1% | 59.7% |
| HumanEval+ | 75% | 82.3% |
| MBPP+ | 70.1% | 75.1% |
| LMArena Coding | — | 1251 |
Reasoning Not comparable
DeepSeek Coder 33B: —, Deepseek Coder v2: 23.6 (#176)
| Benchmark | DeepSeek Coder 33B | Deepseek Coder v2 |
|---|---|---|
| WinoGrande | 62% | 83.7% |
| LMArena Hard Prompts | — | 1207 |
| Epoch Capabilities Index | 96.32 | — |
Math Not comparable
DeepSeek Coder 33B: —, Deepseek Coder v2: 34.9 (#190)
| Benchmark | DeepSeek Coder 33B | Deepseek Coder v2 |
|---|---|---|
| GSM8K | 35.4% | 94.5% |
| LMArena Math | — | 1241 |
Knowledge Not comparable
DeepSeek Coder 33B: —, Deepseek Coder v2: 32.3 (#212)
| Benchmark | DeepSeek Coder 33B | Deepseek Coder v2 |
|---|---|---|
| ARC (AI2) Challenge | 42.2% | 64.3% |
| LMArena Expert | — | 1181 |
| MMLU | 39.4% | — |
Multilingual Not comparable
DeepSeek Coder 33B: —, Deepseek Coder v2: 36.3 (#240)
| Benchmark | DeepSeek Coder 33B | Deepseek Coder v2 |
|---|---|---|
| LMArena Non-English | — | 1182 |
| LMArena Chinese | — | 1201 |
| LMArena French | — | 1185 |
| LMArena German | — | 1164 |
| LMArena Japanese | — | 1126 |
| LMArena Korean | — | 1104 |
| LMArena Russian | — | 1188 |
| LMArena Spanish | — | 1153 |
Instruction Following Not comparable
DeepSeek Coder 33B: —, Deepseek Coder v2: 61.7 (#242)
| Benchmark | DeepSeek Coder 33B | Deepseek Coder v2 |
|---|---|---|
| LMArena Instruction Following | — | 1180 |
Long Context Not comparable
DeepSeek Coder 33B: —, Deepseek Coder v2: 37.0 (#224)
| Benchmark | DeepSeek Coder 33B | Deepseek Coder v2 |
|---|---|---|
| LMArena Longer Query | — | 1219 |
Writing & Preference Not comparable
DeepSeek Coder 33B: —, Deepseek Coder v2: 38.2 (#253)
| Benchmark | DeepSeek Coder 33B | Deepseek Coder v2 |
|---|---|---|
| LMArena Text | — | 1191 |
| LMArena Creative Writing | — | 1120 |
| LMArena Multi-Turn | — | 1177 |
Frequently asked questions
Is DeepSeek Coder 33B better than Deepseek Coder v2?
Deepseek Coder v2 has enough public results to be ranked (#220); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 33B or Deepseek Coder v2 better for coding?
They score almost the same on coding (38.0 vs 38.1); test both on your own repository before choosing.
How many benchmarks do DeepSeek Coder 33B and Deepseek Coder v2 share?
7 benchmarks have published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Deepseek Coder v2 has 24.