Model comparison
DeepSeek LLM 67B vs Qwen2.5 Plus 1127
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.8 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 Qwen2.5 Plus 1127 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5 Plus 1127 leads 35.5 to 7.0.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.9 | 38.8 |
| Released | 2023-11-29 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 Plus 1127 leads
DeepSeek LLM 67B: 31.9 (#278), Qwen2.5 Plus 1127: 38.5 (#175)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Coding | 1096 | 1314 |
Reasoning Qwen2.5 Plus 1127 leads
DeepSeek LLM 67B: 16.5 (#304), Qwen2.5 Plus 1127: 25.9 (#141)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1299 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math Qwen2.5 Plus 1127 leads
DeepSeek LLM 67B: 8.7 (#324), Qwen2.5 Plus 1127: 36.1 (#174)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | 1108 | 1298 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Qwen2.5 Plus 1127 leads
DeepSeek LLM 67B: 7.0 (#313), Qwen2.5 Plus 1127: 35.5 (#183)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 Plus 1127 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1289 |
Multilingual Qwen2.5 Plus 1127 leads
DeepSeek LLM 67B: 29.4 (#267), Qwen2.5 Plus 1127: 41.9 (#201)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | 1073 | 1265 |
| LMArena Chinese | 1132 | 1314 |
| LMArena German | — | 1231 |
| LMArena Japanese | — | 1207 |
| LMArena Russian | — | 1271 |
Instruction Following Qwen2.5 Plus 1127 leads
DeepSeek LLM 67B: 55.4 (#277), Qwen2.5 Plus 1127: 67.2 (#199)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1275 |
Long Context Qwen2.5 Plus 1127 leads
DeepSeek LLM 67B: 33.1 (#265), Qwen2.5 Plus 1127: 39.2 (#184)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | 1092 | 1292 |
Writing & Preference Qwen2.5 Plus 1127 leads
DeepSeek LLM 67B: 31.6 (#282), Qwen2.5 Plus 1127: 49.4 (#192)
| Benchmark | DeepSeek LLM 67B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | 1105 | 1299 |
| LMArena Creative Writing | 1067 | 1262 |
| LMArena Multi-Turn | 1082 | 1299 |
Frequently asked questions
Is DeepSeek LLM 67B better than Qwen2.5 Plus 1127?
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.8 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Qwen2.5 Plus 1127 better for coding?
Qwen2.5 Plus 1127 scores higher on coding benchmarks: 38.5 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Qwen2.5 Plus 1127 share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen2.5 Plus 1127 has 14.