Model comparison
Qwen1.5-72B vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 30.8 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 37.3.
- Qwen1.5-72B has downloadable open weights; the other is API-only.
Side by side
| Qwen1.5-72B | Sonar | |
|---|---|---|
| Provider | Alibaba (Qwen) | Perplexity |
| Noometry Index | 30.8 | 38.5 |
| 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 | 22 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Qwen1.5-72B: 31.9 (#277), Sonar: 35.7 (#221)
| Benchmark | Qwen1.5-72B | Sonar |
|---|---|---|
| BigCodeBench Instruct | 33.2% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1165 | — |
| BigCodeBench Complete | 40.3% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 61.6% | — |
Reasoning Qwen1.5-72B leads
Qwen1.5-72B: 22.2 (#203), Sonar: 21.1 (#227)
| Benchmark | Qwen1.5-72B | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1148 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math Too close to call
Qwen1.5-72B: 33.2 (#205), Sonar: 33.7 (#200)
| Benchmark | Qwen1.5-72B | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1164 | — |
Knowledge Not comparable
Qwen1.5-72B: 11.5 (#300), Sonar: —
| Benchmark | Qwen1.5-72B | Sonar |
|---|---|---|
| GPQA Diamond | 28.8% | — |
| LMArena Expert | 1136 | — |
Multilingual Not comparable
Qwen1.5-72B: 33.2 (#253), Sonar: —
| Benchmark | Qwen1.5-72B | Sonar |
|---|---|---|
| LMArena Non-English | 1135 | — |
| LMArena Chinese | 1186 | — |
| LMArena French | 1159 | — |
| LMArena German | 1084 | — |
| LMArena Japanese | 1061 | — |
| LMArena Korean | 1050 | — |
| LMArena Russian | 1104 | — |
| LMArena Spanish | 1110 | — |
Instruction Following Sonar leads
Qwen1.5-72B: 59.3 (#256), Sonar: 71.4 (#150)
| Benchmark | Qwen1.5-72B | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1141 | — |
Long Context Not comparable
Qwen1.5-72B: 35.1 (#243), Sonar: —
| Benchmark | Qwen1.5-72B | Sonar |
|---|---|---|
| LMArena Longer Query | 1157 | — |
Writing & Preference Sonar leads
Qwen1.5-72B: 37.3 (#258), Sonar: 52.6 (#167)
| Benchmark | Qwen1.5-72B | Sonar |
|---|---|---|
| LMArena Text | 1166 | — |
| LMArena Creative Writing | 1137 | — |
| LMArena Multi-Turn | 1160 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Qwen1.5-72B better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 30.8 on the Noometry Index.
Is Qwen1.5-72B or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.7 versus 31.9 in the Noometry coding category.
How many benchmarks do Qwen1.5-72B and Sonar share?
0 benchmarks have published results for both models. Qwen1.5-72B has 22 scored results on Noometry and Sonar has 7.