Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Qwen-7B
Neither DeepSeek-V2 (MoE-236B, May 2024) nor Qwen-7B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 5 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Qwen-7B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 40.3 | — |
| Released | 2024-05-07 | 2023-09-28 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), Qwen-7B: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen-7B |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| BigCodeBench Complete | 59.4% | — |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Qwen-7B: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen-7B |
|---|---|---|
| BIG-Bench Hard | 78.8% | 45% |
| Epoch Capabilities Index | 124.77 | 106.83 |
| PIQA | 83.9% | 77.9% |
| HellaSwag | 87.1% | — |
| LAMBADA | — | 67.9% |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Qwen-7B: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen-7B |
|---|---|---|
| GSM8K | — | 51.7% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Qwen-7B: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen-7B |
|---|---|---|
| ARC (AI2) Challenge | 92.2% | 75.3% |
| MMLU | 78.4% | 45% |
| BoolQ | — | 76.4% |
| TriviaQA | 80% | — |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Qwen-7B?
Neither DeepSeek-V2 (MoE-236B, May 2024) nor Qwen-7B has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Qwen-7B share?
5 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Qwen-7B has 8.