Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs StarCoder 2 15B
Neither DeepSeek-V2 (MoE-236B, May 2024) nor StarCoder 2 15B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 5 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 5 benchmarks with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and StarCoder 2 15B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 36.6.
- The biggest single-benchmark swing is BigCodeBench Complete: 59.4% for DeepSeek-V2 (MoE-236B, May 2024) and 38.4% for StarCoder 2 15B.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | StarCoder 2 15B | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 40.3 | 38.1 |
| Released | 2024-05-07 | 2024-02-20 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), StarCoder 2 15B: 36.6
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | StarCoder 2 15B |
|---|---|---|
| BigCodeBench Complete | 59.4% | 38.4% |
| BigCodeBench Instruct | 48.9% | — |
| HumanEval+ | — | 37.8% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, StarCoder 2 15B: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | StarCoder 2 15B |
|---|---|---|
| Epoch Capabilities Index | 124.77 | 105 |
| WinoGrande | 86.3% | 64.3% |
| BIG-Bench Hard | 78.8% | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, StarCoder 2 15B: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | StarCoder 2 15B |
|---|---|---|
| GSM8K | — | 57.7% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, StarCoder 2 15B: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | StarCoder 2 15B |
|---|---|---|
| ARC (AI2) Challenge | 92.2% | 47.2% |
| MMLU | 78.4% | 64.1% |
| TriviaQA | 80% | — |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than StarCoder 2 15B?
Neither DeepSeek-V2 (MoE-236B, May 2024) nor StarCoder 2 15B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Is DeepSeek-V2 (MoE-236B, May 2024) or StarCoder 2 15B better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 36.6 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and StarCoder 2 15B share?
5 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and StarCoder 2 15B has 7.