Model comparison
Qwen1.5-32B vs Sonar
Sonar is the stronger model overall, scoring 37.8 to 30.0 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
PerplexitySummary
- The widest gap is in writing & preference, where Sonar leads 52.6 to 34.4.
- Qwen1.5-32B has downloadable open weights; the other is API-only.
Side by side
| Qwen1.5-32B | Sonar | |
|---|---|---|
| Provider | Alibaba (Qwen) | Perplexity |
| Noometry Index | 30.0 | 37.8 |
| Released | 2024-02-04 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 21 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Qwen1.5-32B: 31.1 (#278), Sonar: 35.1 (#217)
| Benchmark | Qwen1.5-32B | Sonar |
|---|---|---|
| BigCodeBench Instruct | 32.3% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1155 | — |
| BigCodeBench Complete | 42% | — |
Reasoning Too close to call
Qwen1.5-32B: 20.9 (#210), Sonar: 20.3 (#221)
| Benchmark | Qwen1.5-32B | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1131 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math Too close to call
Qwen1.5-32B: 30.5 (#207), Sonar: 31.3 (#197)
| Benchmark | Qwen1.5-32B | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1155 | — |
Knowledge Not comparable
Qwen1.5-32B: 13.5 (#291), Sonar: —
| Benchmark | Qwen1.5-32B | Sonar |
|---|---|---|
| GPQA Diamond | 30.7% | — |
| LMArena Expert | 1126 | — |
| MMLU | 74.4% | — |
Multilingual Not comparable
Qwen1.5-32B: 31.6 (#254), Sonar: —
| Benchmark | Qwen1.5-32B | Sonar |
|---|---|---|
| LMArena Non-English | 1106 | — |
| LMArena Chinese | 1176 | — |
| LMArena French | 1100 | — |
| LMArena German | 1058 | — |
| LMArena Japanese | 1027 | — |
| LMArena Korean | 1007 | — |
| LMArena Russian | 1073 | — |
| LMArena Spanish | 1089 | — |
Instruction Following Sonar leads
Qwen1.5-32B: 58.0 (#260), Sonar: 71.5 (#146)
| Benchmark | Qwen1.5-32B | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1116 | — |
Long Context Not comparable
Qwen1.5-32B: 34.7 (#241), Sonar: —
| Benchmark | Qwen1.5-32B | Sonar |
|---|---|---|
| LMArena Longer Query | 1146 | — |
Writing & Preference Sonar leads
Qwen1.5-32B: 34.4 (#266), Sonar: 52.6 (#166)
| Benchmark | Qwen1.5-32B | Sonar |
|---|---|---|
| LMArena Text | 1137 | — |
| LMArena Creative Writing | 1083 | — |
| LMArena Multi-Turn | 1140 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Qwen1.5-32B better than Sonar?
Sonar is the stronger model overall, scoring 37.8 to 30.0 on the Noometry Index.
Is Qwen1.5-32B or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.1 versus 31.1 in the Noometry coding category.
How many benchmarks do Qwen1.5-32B and Sonar share?
0 benchmarks have published results for both models. Qwen1.5-32B has 21 scored results on Noometry and Sonar has 7.