Model comparison
DeepSeek LLM 67B vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 24.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Max leads 36.9 to 8.7.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Qwen2.5-Max | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.9 | 40.7 |
| Released | 2023-11-29 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
DeepSeek LLM 67B: 31.9 (#278), Qwen2.5-Max: 41.8 (#117)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1096 | 1359 |
| LiveBench Coding | — | 64.4% |
Reasoning Qwen2.5-Max leads
DeepSeek LLM 67B: 16.5 (#304), Qwen2.5-Max: 25.6 (#147)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1360 |
| Epoch Capabilities Index | 110.5 | 132.53 |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| LiveBench | — | 62.3% |
Math Qwen2.5-Max leads
DeepSeek LLM 67B: 8.7 (#324), Qwen2.5-Max: 36.9 (#162)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1108 | 1369 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| LiveBench Math | — | 58.4% |
| MATH Level 5 | 6.4% | — |
Knowledge Qwen2.5-Max leads
DeepSeek LLM 67B: 7.0 (#313), Qwen2.5-Max: 35.3 (#186)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Max |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| Confabulations | — | 21.8% |
| LMArena Expert | — | 1337 |
Multilingual Qwen2.5-Max leads
DeepSeek LLM 67B: 29.4 (#267), Qwen2.5-Max: 48.1 (#146)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1073 | 1352 |
| LMArena Chinese | 1132 | 1382 |
| LMArena French | — | 1396 |
| LMArena German | — | 1350 |
| LMArena Japanese | — | 1300 |
| LMArena Korean | — | 1304 |
| LMArena Russian | — | 1353 |
| LMArena Spanish | — | 1377 |
Instruction Following Qwen2.5-Max leads
DeepSeek LLM 67B: 55.4 (#277), Qwen2.5-Max: 71.3 (#152)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1079 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Qwen2.5-Max leads
DeepSeek LLM 67B: 33.1 (#265), Qwen2.5-Max: 41.4 (#142)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1092 | 1358 |
Writing & Preference Qwen2.5-Max leads
DeepSeek LLM 67B: 31.6 (#282), Qwen2.5-Max: 55.4 (#146)
| Benchmark | DeepSeek LLM 67B | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1105 | 1367 |
| LMArena Creative Writing | 1067 | 1339 |
| LMArena Multi-Turn | 1082 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is DeepSeek LLM 67B better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Qwen2.5-Max share?
11 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen2.5-Max has 27.