Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs QwQ-32B
QwQ-32B has enough public results to be ranked (#153); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 3 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and QwQ-32B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 39.8 to 34.9.
- The biggest single-benchmark swing is BigCodeBench Complete: 59.4% for DeepSeek-V2 (MoE-236B, May 2024) and 54.4% for QwQ-32B.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | QwQ-32B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 39.7 | 39.4 |
| Released | 2024-05-07 | 2024-11-28 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141), QwQ-32B: 34.9 (#220)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | QwQ-32B |
|---|---|---|
| BigCodeBench Instruct | 48.9% | 44.6% |
| BigCodeBench Complete | 59.4% | 54.4% |
| Aider Polyglot | — | 20.9% |
| LiveBench Coding | — | 72.2% |
| LMArena Coding | — | 1333 |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, QwQ-32B: 22.9 (#171)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | QwQ-32B |
|---|---|---|
| Epoch Capabilities Index | 124.78 | 137.6 |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | — | 83.5% |
| LMArena Hard Prompts | — | 1326 |
| LiveBench Data Analysis | — | 65% |
| BIG-Bench Hard | 78.8% | — |
| ForecastBench | — | 58.3 |
| HellaSwag | 87.1% | — |
| LiveBench | — | 72% |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, QwQ-32B: 36.2 (#123)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| LiveBench Math | — | 77.8% |
| LMArena Math | — | 1359 |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, QwQ-32B: 37.2 (#150)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | QwQ-32B |
|---|---|---|
| GPQA Diamond | — | 65.3% |
| Confabulations | — | 15.6% |
| LMArena Expert | — | 1323 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, QwQ-32B: 45.0 (#171)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | QwQ-32B |
|---|---|---|
| LMArena Non-English | — | 1306 |
| LMArena Chinese | — | 1378 |
| LMArena French | — | 1337 |
| LMArena German | — | 1313 |
| LMArena Japanese | — | 1263 |
| LMArena Korean | — | 1278 |
| LMArena Russian | — | 1297 |
| LMArena Spanish | — | 1353 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, QwQ-32B: 72.8 (#131)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | QwQ-32B |
|---|---|---|
| LiveBench Instruction Following | — | 81.8% |
| LMArena Instruction Following | — | 1297 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, QwQ-32B: 49.0 (#11)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | QwQ-32B |
|---|---|---|
| Fiction.LiveBench | — | 83.3% |
| LMArena Longer Query | — | 1308 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, QwQ-32B: 50.9 (#175)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | QwQ-32B |
|---|---|---|
| LMArena Text | — | 1329 |
| LMArena Creative Writing | — | 1288 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| LMArena Multi-Turn | — | 1314 |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than QwQ-32B?
QwQ-32B has enough public results to be ranked (#153); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or QwQ-32B better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 39.8 versus 34.9 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and QwQ-32B share?
3 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and QwQ-32B has 36.