Model comparison
Qwen Plus vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 37.1 on the Noometry Index. Qwen Plus costs 1.7× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
PerplexitySummary
- The widest gap is in math, where Sonar leads 33.7 to 23.3.
- Qwen Plus is cheaper at $0.40 / $1.20 per million input/output tokens, against $1 / $1 for Sonar.
- Qwen Plus accepts more context: 1M tokens versus 128K.
Side by side
| Qwen Plus | Sonar | |
|---|---|---|
| Provider | Alibaba (Qwen) | Perplexity |
| Noometry Index | 37.1 | 38.5 |
| Released | 2024-01-25 | 2024-01-01 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 128K |
| Max output | 33K | 4K |
| Input $ / M tokens | $0.40 | $1 |
| Output $ / M tokens | $1.20 | $1 |
| Results tracked | 20 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
Qwen Plus: 38.9 (#167), Sonar: 35.7 (#221)
| Benchmark | Qwen Plus | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1328 | — |
Reasoning Qwen Plus leads
Qwen Plus: 28.4 (#107), Sonar: 21.1 (#227)
| Benchmark | Qwen Plus | Sonar |
|---|---|---|
| Kagi LLM Benchmark | 63.3% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1317 | — |
| DTBench | 81.1% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 24% | — |
| LiveBench | — | 46.9% |
Math Sonar leads
Qwen Plus: 23.3 (#271), Sonar: 33.7 (#200)
| Benchmark | Qwen Plus | Sonar |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 17.8% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1326 | — |
| MATH Level 5 | 65.3% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Not comparable
Qwen Plus: 27.4 (#251), Sonar: —
| Benchmark | Qwen Plus | Sonar |
|---|---|---|
| GPQA Diamond | 48.1% | — |
| LMArena Expert | 1328 | — |
Multilingual Not comparable
Qwen Plus: 45.1 (#175), Sonar: —
| Benchmark | Qwen Plus | Sonar |
|---|---|---|
| LMArena Non-English | 1310 | — |
| LMArena Chinese | 1347 | — |
| LMArena Japanese | 1251 | — |
| LMArena Russian | 1323 | — |
Instruction Following Sonar leads
Qwen Plus: 68.8 (#181), Sonar: 71.4 (#150)
| Benchmark | Qwen Plus | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1303 | — |
Long Context Not comparable
Qwen Plus: 40.3 (#158), Sonar: —
| Benchmark | Qwen Plus | Sonar |
|---|---|---|
| LMArena Longer Query | 1324 | — |
Writing & Preference Too close to call
Qwen Plus: 52.2 (#176), Sonar: 52.6 (#167)
| Benchmark | Qwen Plus | Sonar |
|---|---|---|
| LMArena Text | 1326 | — |
| LMArena Creative Writing | 1293 | — |
| LMArena Multi-Turn | 1336 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Qwen Plus better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 37.1 on the Noometry Index. Qwen Plus costs 1.7× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.
Which is cheaper, Qwen Plus or Sonar?
Qwen Plus is cheaper. It lists at $0.40 per million input tokens and $1.20 per million output tokens; Sonar lists at $1 and $1.
Is Qwen Plus or Sonar better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
Qwen Plus does, with 1M tokens against 128K.
How many benchmarks do Qwen Plus and Sonar share?
0 benchmarks have published results for both models. Qwen Plus has 20 scored results on Noometry and Sonar has 7.