Model comparison
Qwen2.5-Max vs Sonar
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 38.5 on the Noometry Index.
Last verified . 7 shared benchmarks.
Alibaba (Qwen)
PerplexitySummary
- They share 7 benchmarks with published results for both. Qwen2.5-Max scores higher in 4 categories and Sonar in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen2.5-Max leads 41.8 to 35.7.
- The biggest single-benchmark swing is LiveBench Data Analysis: 67.9% for Qwen2.5-Max and 37.9% for Sonar.
Side by side
| Qwen2.5-Max | Sonar | |
|---|---|---|
| Provider | Alibaba (Qwen) | Perplexity |
| Noometry Index | 40.7 | 38.5 |
| Released | 2025-01-25 | 2024-01-01 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 27 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Qwen2.5-Max: 41.8 (#117), Sonar: 35.7 (#221)
| Benchmark | Qwen2.5-Max | Sonar |
|---|---|---|
| LiveBench Coding | 64.4% | 35.1% |
| LMArena Coding | 1359 | — |
Reasoning Qwen2.5-Max leads
Qwen2.5-Max: 25.6 (#147), Sonar: 21.1 (#227)
| Benchmark | Qwen2.5-Max | Sonar |
|---|---|---|
| LiveBench Reasoning | 51.4% | 46.3% |
| LiveBench Data Analysis | 67.9% | 37.9% |
| LiveBench | 62.3% | 46.9% |
| LMArena Hard Prompts | 1360 | — |
| Epoch Capabilities Index | 132.53 | — |
Math Qwen2.5-Max leads
Qwen2.5-Max: 36.9 (#162), Sonar: 33.7 (#200)
| Benchmark | Qwen2.5-Max | Sonar |
|---|---|---|
| LiveBench Math | 58.4% | 41.6% |
| LMArena Math | 1369 | — |
Knowledge Not comparable
Qwen2.5-Max: 35.3 (#186), Sonar: —
| Benchmark | Qwen2.5-Max | Sonar |
|---|---|---|
| Confabulations | 21.8% | — |
| LMArena Expert | 1337 | — |
Multilingual Not comparable
Qwen2.5-Max: 48.1 (#146), Sonar: —
| Benchmark | Qwen2.5-Max | Sonar |
|---|---|---|
| LMArena Non-English | 1352 | — |
| LMArena Chinese | 1382 | — |
| LMArena French | 1396 | — |
| LMArena German | 1350 | — |
| LMArena Japanese | 1300 | — |
| LMArena Korean | 1304 | — |
| LMArena Russian | 1353 | — |
| LMArena Spanish | 1377 | — |
Instruction Following Too close to call
Qwen2.5-Max: 71.3 (#152), Sonar: 71.4 (#150)
| Benchmark | Qwen2.5-Max | Sonar |
|---|---|---|
| LiveBench Instruction Following | 75.3% | 76.2% |
| LMArena Instruction Following | 1335 | — |
Long Context Not comparable
Qwen2.5-Max: 41.4 (#142), Sonar: —
| Benchmark | Qwen2.5-Max | Sonar |
|---|---|---|
| LMArena Longer Query | 1358 | — |
Writing & Preference Qwen2.5-Max leads
Qwen2.5-Max: 55.4 (#146), Sonar: 52.6 (#167)
| Benchmark | Qwen2.5-Max | Sonar |
|---|---|---|
| LiveBench Language | 56.3% | 44.1% |
| LMArena Text | 1367 | — |
| LMArena Creative Writing | 1339 | — |
| Short-Story Creative Writing | 72.9% | — |
| LMArena Multi-Turn | 1364 | — |
Frequently asked questions
Is Qwen2.5-Max better than Sonar?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 38.5 on the Noometry Index.
Is Qwen2.5-Max or Sonar better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 35.7 in the Noometry coding category.
How many benchmarks do Qwen2.5-Max and Sonar share?
7 benchmarks have published results for both models. Qwen2.5-Max has 27 scored results on Noometry and Sonar has 7.