Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Qwen1.5-14B
Qwen1.5-14B has enough public results to be ranked (#250); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and Qwen1.5-14B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 39.8 to 32.5.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Qwen1.5-14B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 39.7 | 32.1 |
| Released | 2024-05-07 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 17 |
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): 39.8 (#141), Qwen1.5-14B: 32.5 (#259)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen1.5-14B |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1138 |
| BigCodeBench Complete | 59.4% | — |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Qwen1.5-14B: 20.5 (#217)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | — | 1113 |
| BIG-Bench Hard | 78.8% | — |
| Epoch Capabilities Index | 124.78 | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Qwen1.5-14B: 29.9 (#214)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen1.5-14B |
|---|---|---|
| LMArena Math | — | 1125 |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Qwen1.5-14B: 29.3 (#230)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen1.5-14B |
|---|---|---|
| MMLU | 78.4% | 68.6% |
| LMArena Expert | — | 1094 |
| ARC (AI2) Challenge | 92.2% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Qwen1.5-14B: 30.8 (#257)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | — | 1095 |
| LMArena Chinese | — | 1147 |
| LMArena French | — | 1115 |
| LMArena German | — | 1043 |
| LMArena Japanese | — | 1019 |
| LMArena Russian | — | 1046 |
| LMArena Spanish | — | 1085 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Qwen1.5-14B: 57.1 (#266)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | — | 1102 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Qwen1.5-14B: 33.7 (#252)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | — | 1113 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Qwen1.5-14B: 33.7 (#270)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen1.5-14B |
|---|---|---|
| LMArena Text | — | 1128 |
| LMArena Creative Writing | — | 1091 |
| LMArena Multi-Turn | — | 1110 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Qwen1.5-14B?
Qwen1.5-14B has enough public results to be ranked (#250); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Qwen1.5-14B better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 39.8 versus 32.5 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Qwen1.5-14B share?
1 benchmark has published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Qwen1.5-14B has 17.