Model comparison
DeepSeek LLM 67B vs Qwen1.5-14B
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Qwen1.5-14B in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-14B leads 32.4 to 8.7.
Side by side
| DeepSeek LLM 67B | Qwen1.5-14B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.9 | 32.7 |
| Released | 2023-11-29 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-14B leads
DeepSeek LLM 67B: 31.9 (#278), Qwen1.5-14B: 33.1 (#263)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1096 | 1138 |
Reasoning Qwen1.5-14B leads
DeepSeek LLM 67B: 16.5 (#304), Qwen1.5-14B: 21.4 (#223)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1113 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math Qwen1.5-14B leads
DeepSeek LLM 67B: 8.7 (#324), Qwen1.5-14B: 32.4 (#215)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1108 | 1125 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Qwen1.5-14B leads
DeepSeek LLM 67B: 7.0 (#313), Qwen1.5-14B: 29.8 (#232)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-14B |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1094 |
| MMLU | — | 68.6% |
Multilingual Qwen1.5-14B leads
DeepSeek LLM 67B: 29.4 (#267), Qwen1.5-14B: 30.7 (#262)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1073 | 1095 |
| LMArena Chinese | 1132 | 1147 |
| LMArena French | — | 1116 |
| LMArena German | — | 1043 |
| LMArena Japanese | — | 1019 |
| LMArena Russian | — | 1046 |
| LMArena Spanish | — | 1085 |
Instruction Following Qwen1.5-14B leads
DeepSeek LLM 67B: 55.4 (#277), Qwen1.5-14B: 56.8 (#271)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1102 |
Long Context Too close to call
DeepSeek LLM 67B: 33.1 (#265), Qwen1.5-14B: 33.7 (#257)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1092 | 1113 |
Writing & Preference Qwen1.5-14B leads
DeepSeek LLM 67B: 31.6 (#282), Qwen1.5-14B: 33.6 (#276)
| Benchmark | DeepSeek LLM 67B | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1105 | 1128 |
| LMArena Creative Writing | 1067 | 1091 |
| LMArena Multi-Turn | 1082 | 1110 |
Frequently asked questions
Is DeepSeek LLM 67B better than Qwen1.5-14B?
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Qwen1.5-14B better for coding?
Qwen1.5-14B scores higher on coding benchmarks: 33.1 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Qwen1.5-14B share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen1.5-14B has 17.