Model comparison
Qwen-14B vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 31.4 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 27.6.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| Qwen-14B | Sonar | |
|---|---|---|
| Provider | Alibaba (Qwen) | Perplexity |
| Noometry Index | 31.4 | 38.5 |
| Released | 2023-09-24 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 18 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Qwen-14B: 31.2 (#288), Sonar: 35.7 (#221)
| Benchmark | Qwen-14B | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1071 | — |
Reasoning Sonar leads
Qwen-14B: 19.6 (#257), Sonar: 21.1 (#227)
| Benchmark | Qwen-14B | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1027 | — |
| LiveBench Data Analysis | — | 37.9% |
| BIG-Bench Hard | 55% | — |
| Epoch Capabilities Index | 113.03 | — |
| LAMBADA | 71.1% | — |
| LiveBench | — | 46.9% |
| PIQA | 79.9% | — |
Math Sonar leads
Qwen-14B: 31.2 (#227), Sonar: 33.7 (#200)
| Benchmark | Qwen-14B | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1068 | — |
| GSM8K | 61.3% | — |
Knowledge Not comparable
Qwen-14B: —, Sonar: —
| Benchmark | Qwen-14B | Sonar |
|---|---|---|
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |
| MMLU | 66.3% | — |
Multilingual Not comparable
Qwen-14B: 27.5 (#275), Sonar: —
| Benchmark | Qwen-14B | Sonar |
|---|---|---|
| LMArena Non-English | 1041 | — |
| LMArena Chinese | 1077 | — |
Instruction Following Sonar leads
Qwen-14B: 52.4 (#289), Sonar: 71.4 (#150)
| Benchmark | Qwen-14B | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1031 | — |
Long Context Not comparable
Qwen-14B: 31.3 (#280), Sonar: —
| Benchmark | Qwen-14B | Sonar |
|---|---|---|
| LMArena Longer Query | 1028 | — |
Writing & Preference Sonar leads
Qwen-14B: 27.6 (#299), Sonar: 52.6 (#167)
| Benchmark | Qwen-14B | Sonar |
|---|---|---|
| LMArena Text | 1051 | — |
| LMArena Creative Writing | 1028 | — |
| LMArena Multi-Turn | 1022 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Qwen-14B better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 31.4 on the Noometry Index.
Is Qwen-14B or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.7 versus 31.2 in the Noometry coding category.
How many benchmarks do Qwen-14B and Sonar share?
0 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Sonar has 7.