Model comparison
DeepSeek LLM 67B vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.4 to 24.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and Qwen Max in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen Max leads 30.3 to 7.1.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 67.2% for Qwen Max.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Qwen Max | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.8 | 34.4 |
| Released | 2023-11-29 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | — | 33K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.60 |
| Output $ / M tokens | — | $6.40 |
| Results tracked | 15 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek LLM 67B: 31.3 (#273), Qwen Max: 30.3 (#288)
| Benchmark | DeepSeek LLM 67B | Qwen Max |
|---|---|---|
| LMArena Coding | 1096 | 1288 |
| Aider Polyglot | — | 21.8% |
Reasoning Qwen Max leads
DeepSeek LLM 67B: 15.9 (#300), Qwen Max: 24.1 (#154)
| Benchmark | DeepSeek LLM 67B | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1270 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.54 | — |
Math Qwen Max leads
DeepSeek LLM 67B: 8.1 (#318), Qwen Max: 21.0 (#272)
| Benchmark | DeepSeek LLM 67B | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 16.1% |
| LMArena Math | 1108 | 1275 |
| MATH Level 5 | 6.4% | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Qwen Max leads
DeepSeek LLM 67B: 7.1 (#308), Qwen Max: 30.3 (#222)
| Benchmark | DeepSeek LLM 67B | Qwen Max |
|---|---|---|
| GPQA Diamond | 24.6% | 56.1% |
| LMArena Expert | — | 1248 |
Multilingual Qwen Max leads
DeepSeek LLM 67B: 29.5 (#262), Qwen Max: 42.0 (#197)
| Benchmark | DeepSeek LLM 67B | Qwen Max |
|---|---|---|
| LMArena Non-English | 1073 | 1263 |
| LMArena Chinese | 1132 | 1254 |
| LMArena French | — | 1329 |
| LMArena German | — | 1254 |
| LMArena Japanese | — | 1205 |
| LMArena Korean | — | 1141 |
| LMArena Russian | — | 1274 |
| LMArena Spanish | — | 1290 |
Instruction Following Qwen Max leads
DeepSeek LLM 67B: 55.7 (#272), Qwen Max: 66.7 (#203)
| Benchmark | DeepSeek LLM 67B | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1079 | 1262 |
Long Context Qwen Max leads
DeepSeek LLM 67B: 33.1 (#260), Qwen Max: 39.4 (#175)
| Benchmark | DeepSeek LLM 67B | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1092 | 1289 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Qwen Max leads
DeepSeek LLM 67B: 31.8 (#277), Qwen Max: 48.0 (#200)
| Benchmark | DeepSeek LLM 67B | Qwen Max |
|---|---|---|
| LMArena Text | 1105 | 1282 |
| LMArena Creative Writing | 1067 | 1248 |
| LMArena Multi-Turn | 1082 | 1277 |
Frequently asked questions
Is DeepSeek LLM 67B better than Qwen Max?
Qwen Max is the stronger model overall, scoring 34.4 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or Qwen Max better for coding?
They score almost the same on coding (31.3 vs 30.3); test both on your own repository before choosing.
How many benchmarks do DeepSeek LLM 67B and Qwen Max share?
13 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen Max has 23.