Model comparison
Qwen2.5 32B Instruct vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.4 to 29.7 on the Noometry Index.
Last verified . 6 shared benchmarks.
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. Qwen2.5 32B Instruct scores higher in 1 category and QwQ-32B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where QwQ-32B leads 36.2 to 15.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.4% for Qwen2.5 32B Instruct and 59.2% for QwQ-32B.
Side by side
| Qwen2.5 32B Instruct | QwQ-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 29.7 | 39.4 |
| Released | 2024-09 | 2024-11-28 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $2.80 | — |
| Results tracked | 7 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 32B Instruct leads
Qwen2.5 32B Instruct: 38.1 (#165), QwQ-32B: 34.9 (#220)
| Benchmark | Qwen2.5 32B Instruct | QwQ-32B |
|---|---|---|
| BigCodeBench Instruct | 45% | 44.6% |
| BigCodeBench Complete | 52.3% | 54.4% |
| Aider Polyglot | — | 20.9% |
| LiveBench Coding | — | 72.2% |
| LMArena Coding | — | 1333 |
Reasoning QwQ-32B leads
Qwen2.5 32B Instruct: 18.5 (#262), QwQ-32B: 22.9 (#171)
| Benchmark | Qwen2.5 32B Instruct | QwQ-32B |
|---|---|---|
| Chess Puzzles | 0% | 5% |
| Epoch Capabilities Index | 128.52 | 137.6 |
| LiveBench Reasoning | — | 83.5% |
| LMArena Hard Prompts | — | 1326 |
| LiveBench Data Analysis | — | 65% |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |
Math QwQ-32B leads
Qwen2.5 32B Instruct: 15.3 (#289), QwQ-32B: 36.2 (#123)
| Benchmark | Qwen2.5 32B Instruct | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.4% | 59.2% |
| LiveBench Math | — | 77.8% |
| LMArena Math | — | 1359 |
| MATH Level 5 | 56.1% | — |
Knowledge QwQ-32B leads
Qwen2.5 32B Instruct: 24.9 (#259), QwQ-32B: 37.2 (#150)
| Benchmark | Qwen2.5 32B Instruct | QwQ-32B |
|---|---|---|
| GPQA Diamond | 46.1% | 65.3% |
| Confabulations | — | 15.6% |
| LMArena Expert | — | 1323 |
Multilingual Not comparable
Qwen2.5 32B Instruct: —, QwQ-32B: 45.0 (#171)
| Benchmark | Qwen2.5 32B Instruct | 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
Qwen2.5 32B Instruct: —, QwQ-32B: 72.8 (#131)
| Benchmark | Qwen2.5 32B Instruct | QwQ-32B |
|---|---|---|
| LiveBench Instruction Following | — | 81.8% |
| LMArena Instruction Following | — | 1297 |
Long Context Not comparable
Qwen2.5 32B Instruct: —, QwQ-32B: 49.0 (#11)
| Benchmark | Qwen2.5 32B Instruct | QwQ-32B |
|---|---|---|
| Fiction.LiveBench | — | 83.3% |
| LMArena Longer Query | — | 1308 |
Writing & Preference Not comparable
Qwen2.5 32B Instruct: —, QwQ-32B: 50.9 (#175)
| Benchmark | Qwen2.5 32B Instruct | 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 Qwen2.5 32B Instruct better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.4 to 29.7 on the Noometry Index.
Is Qwen2.5 32B Instruct or QwQ-32B better for coding?
Qwen2.5 32B Instruct scores higher on coding benchmarks: 38.1 versus 34.9 in the Noometry coding category.
How many benchmarks do Qwen2.5 32B Instruct and QwQ-32B share?
6 benchmarks have published results for both models. Qwen2.5 32B Instruct has 7 scored results on Noometry and QwQ-32B has 36.