Model comparison
QwQ-32B vs Sonar
QwQ-32B is the stronger model overall, scoring 39.8 to 38.5 on the Noometry Index.
Last verified . 7 shared benchmarks.
Alibaba (Qwen)
PerplexitySummary
- They share 7 benchmarks with published results for both. QwQ-32B scores higher in 3 categories and Sonar in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where QwQ-32B leads 38.0 to 33.7.
- The biggest single-benchmark swing is LiveBench Reasoning: 83.5% for QwQ-32B and 46.3% for Sonar.
- QwQ-32B has downloadable open weights; the other is API-only.
Side by side
| QwQ-32B | Sonar | |
|---|---|---|
| Provider | Alibaba (Qwen) | Perplexity |
| Noometry Index | 39.8 | 38.5 |
| Released | 2024-11-28 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 36 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
QwQ-32B: 35.4 (#226), Sonar: 35.7 (#221)
| Benchmark | QwQ-32B | Sonar |
|---|---|---|
| LiveBench Coding | 72.2% | 35.1% |
| Aider Polyglot | 20.9% | — |
| BigCodeBench Instruct | 44.6% | — |
| LMArena Coding | 1333 | — |
| BigCodeBench Complete | 54.4% | — |
Reasoning QwQ-32B leads
QwQ-32B: 23.7 (#174), Sonar: 21.1 (#227)
| Benchmark | QwQ-32B | Sonar |
|---|---|---|
| LiveBench Reasoning | 83.5% | 46.3% |
| LiveBench Data Analysis | 65% | 37.9% |
| LiveBench | 72% | 46.9% |
| Chess Puzzles | 5% | — |
| LMArena Hard Prompts | 1325 | — |
| Epoch Capabilities Index | 137.6 | — |
| ForecastBench | 58.3 | — |
Math QwQ-32B leads
QwQ-32B: 38.0 (#143), Sonar: 33.7 (#200)
| Benchmark | QwQ-32B | Sonar |
|---|---|---|
| LiveBench Math | 77.8% | 41.6% |
| OTIS Mock AIME 2024-2025 | 59.2% | — |
| LMArena Math | 1359 | — |
Knowledge Not comparable
QwQ-32B: 37.2 (#158), Sonar: —
| Benchmark | QwQ-32B | Sonar |
|---|---|---|
| GPQA Diamond | 65.3% | — |
| Confabulations | 15.6% | — |
| LMArena Expert | 1324 | — |
Multilingual Not comparable
QwQ-32B: 44.8 (#176), Sonar: —
| Benchmark | QwQ-32B | Sonar |
|---|---|---|
| LMArena Non-English | 1305 | — |
| LMArena Chinese | 1378 | — |
| LMArena French | 1336 | — |
| LMArena German | 1313 | — |
| LMArena Japanese | 1262 | — |
| LMArena Korean | 1279 | — |
| LMArena Russian | 1297 | — |
| LMArena Spanish | 1354 | — |
Instruction Following QwQ-32B leads
QwQ-32B: 72.6 (#137), Sonar: 71.4 (#150)
| Benchmark | QwQ-32B | Sonar |
|---|---|---|
| LiveBench Instruction Following | 81.8% | 76.2% |
| LMArena Instruction Following | 1297 | — |
Long Context Not comparable
QwQ-32B: 49.0 (#11), Sonar: —
| Benchmark | QwQ-32B | Sonar |
|---|---|---|
| Fiction.LiveBench | 83.3% | — |
| LMArena Longer Query | 1308 | — |
Writing & Preference Sonar leads
QwQ-32B: 50.6 (#180), Sonar: 52.6 (#167)
| Benchmark | QwQ-32B | Sonar |
|---|---|---|
| LiveBench Language | 51.4% | 44.1% |
| LMArena Text | 1329 | — |
| LMArena Creative Writing | 1288 | — |
| Short-Story Creative Writing | 80.2% | — |
| EQ-Bench Creative Writing | 1257 | — |
| LMArena Multi-Turn | 1314 | — |
Frequently asked questions
Is QwQ-32B better than Sonar?
QwQ-32B is the stronger model overall, scoring 39.8 to 38.5 on the Noometry Index.
Is QwQ-32B or Sonar better for coding?
They score almost the same on coding (35.4 vs 35.7); test both on your own repository before choosing.
How many benchmarks do QwQ-32B and Sonar share?
7 benchmarks have published results for both models. QwQ-32B has 36 scored results on Noometry and Sonar has 7.