Model comparison
Deepseek Coder v2 vs DeepSeek-V2 (MoE-236B, May 2024)
Deepseek Coder v2 has enough public results to be ranked (#220); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 4 shared benchmarks.
DeepSeekSummary
- They share 4 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and DeepSeek-V2 (MoE-236B, May 2024) in 1 category; one gap is clear of the uncertainty.
Side by side
| Deepseek Coder v2 | DeepSeek-V2 (MoE-236B, May 2024) | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 35.9 | 40.3 |
| Released | 2024-06-17 | 2024-05-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
Deepseek Coder v2: 38.1 (#183), DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139)
| Benchmark | Deepseek Coder v2 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| BigCodeBench Instruct | 48.2% | 48.9% |
| BigCodeBench Complete | 59.7% | 59.4% |
| LMArena Coding | 1251 | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Not comparable
Deepseek Coder v2: 23.6 (#176), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Deepseek Coder v2 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| WinoGrande | 83.7% | 86.3% |
| LMArena Hard Prompts | 1207 | — |
| BIG-Bench Hard | — | 78.8% |
| Epoch Capabilities Index | — | 124.77 |
| HellaSwag | — | 87.1% |
| PIQA | — | 83.9% |
Math Not comparable
Deepseek Coder v2: 34.9 (#190), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Deepseek Coder v2 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Math | 1241 | — |
| GSM8K | 94.5% | — |
Knowledge Not comparable
Deepseek Coder v2: 32.3 (#212), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Deepseek Coder v2 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| ARC (AI2) Challenge | 64.3% | 92.2% |
| LMArena Expert | 1181 | — |
| MMLU | — | 78.4% |
| TriviaQA | — | 80% |
Multilingual Not comparable
Deepseek Coder v2: 36.3 (#240), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Deepseek Coder v2 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| 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 v2: 61.7 (#242), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Deepseek Coder v2 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Instruction Following | 1180 | — |
Long Context Not comparable
Deepseek Coder v2: 37.0 (#224), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Deepseek Coder v2 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Longer Query | 1219 | — |
Writing & Preference Not comparable
Deepseek Coder v2: 38.2 (#253), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Deepseek Coder v2 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1120 | — |
| LMArena Multi-Turn | 1177 | — |
Frequently asked questions
Is Deepseek Coder v2 better than DeepSeek-V2 (MoE-236B, May 2024)?
Deepseek Coder v2 has enough public results to be ranked (#220); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is Deepseek Coder v2 or DeepSeek-V2 (MoE-236B, May 2024) better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and DeepSeek-V2 (MoE-236B, May 2024) share?
4 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and DeepSeek-V2 (MoE-236B, May 2024) has 10.