Model comparison
DeepSeek LLM 67B vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.4 to 24.8 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and QwQ-32B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where QwQ-32B leads 37.2 to 7.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 59.2% for QwQ-32B.
Side by side
| DeepSeek LLM 67B | QwQ-32B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.8 | 39.4 |
| Released | 2023-11-29 | 2024-11-28 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding QwQ-32B leads
DeepSeek LLM 67B: 31.3 (#273), QwQ-32B: 34.9 (#220)
| Benchmark | DeepSeek LLM 67B | QwQ-32B |
|---|---|---|
| LMArena Coding | 1096 | 1333 |
| Aider Polyglot | — | 20.9% |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
Reasoning QwQ-32B leads
DeepSeek LLM 67B: 15.9 (#300), QwQ-32B: 22.9 (#171)
| Benchmark | DeepSeek LLM 67B | QwQ-32B |
|---|---|---|
| Chess Puzzles | 0% | 5% |
| LMArena Hard Prompts | 1070 | 1326 |
| Epoch Capabilities Index | 110.54 | 137.6 |
| LiveBench Reasoning | — | 83.5% |
| LiveBench Data Analysis | — | 65% |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |
Math QwQ-32B leads
DeepSeek LLM 67B: 8.1 (#318), QwQ-32B: 36.2 (#123)
| Benchmark | DeepSeek LLM 67B | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 59.2% |
| LMArena Math | 1108 | 1359 |
| LiveBench Math | — | 77.8% |
| MATH Level 5 | 6.4% | — |
Knowledge QwQ-32B leads
DeepSeek LLM 67B: 7.1 (#308), QwQ-32B: 37.2 (#150)
| Benchmark | DeepSeek LLM 67B | QwQ-32B |
|---|---|---|
| GPQA Diamond | 24.6% | 65.3% |
| Confabulations | — | 15.6% |
| LMArena Expert | — | 1323 |
Multilingual QwQ-32B leads
DeepSeek LLM 67B: 29.5 (#262), QwQ-32B: 45.0 (#171)
| Benchmark | DeepSeek LLM 67B | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1073 | 1306 |
| LMArena Chinese | 1132 | 1378 |
| LMArena French | — | 1337 |
| LMArena German | — | 1313 |
| LMArena Japanese | — | 1263 |
| LMArena Korean | — | 1278 |
| LMArena Russian | — | 1297 |
| LMArena Spanish | — | 1353 |
Instruction Following QwQ-32B leads
DeepSeek LLM 67B: 55.7 (#272), QwQ-32B: 72.8 (#131)
| Benchmark | DeepSeek LLM 67B | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
DeepSeek LLM 67B: 33.1 (#260), QwQ-32B: 49.0 (#11)
| Benchmark | DeepSeek LLM 67B | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1092 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference QwQ-32B leads
DeepSeek LLM 67B: 31.8 (#277), QwQ-32B: 50.9 (#175)
| Benchmark | DeepSeek LLM 67B | QwQ-32B |
|---|---|---|
| LMArena Text | 1105 | 1329 |
| LMArena Creative Writing | 1067 | 1288 |
| LMArena Multi-Turn | 1082 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is DeepSeek LLM 67B better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.4 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or QwQ-32B better for coding?
QwQ-32B scores higher on coding benchmarks: 34.9 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and QwQ-32B share?
14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and QwQ-32B has 36.