Model comparison
Qwen2.5 72B Instruct vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 31.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
PerplexitySummary
- The widest gap is in math, where Sonar leads 33.7 to 19.3.
- Sonar is cheaper at $1 / $1 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct accepts more context: 131K tokens versus 128K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5 72B Instruct | Sonar | |
|---|---|---|
| Provider | Alibaba (Qwen) | Perplexity |
| Noometry Index | 31.9 | 38.5 |
| Released | 2024-09 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 131K | 128K |
| Max output | 8K | 4K |
| Input $ / M tokens | $1.40 | $1 |
| Output $ / M tokens | $5.60 | $1 |
| Results tracked | 43 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Qwen2.5 72B Instruct: 33.2 (#260), Sonar: 35.7 (#221)
| Benchmark | Qwen2.5 72B Instruct | Sonar |
|---|---|---|
| WeirdML | 16% | — |
| BigCodeBench Instruct | 45.8% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1292 | — |
| BigCodeBench Complete | 55.9% | — |
Agentic & Tool Use Not comparable
Qwen2.5 72B Instruct: 22.1 (#133), Sonar: —
| Benchmark | Qwen2.5 72B Instruct | Sonar |
|---|---|---|
| TheAgentCompany | 5.7% | — |
| BALROG | 16.2% | — |
| METR Time Horizons | 35.8% | — |
Reasoning Qwen2.5 72B Instruct leads
Qwen2.5 72B Instruct: 22.3 (#199), Sonar: 21.1 (#227)
| Benchmark | Qwen2.5 72B Instruct | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1271 | — |
| DTBench | 62.9% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 13.4% | — |
| BIG-Bench Hard | 79.8% | — |
| Epoch Capabilities Index | 129 | — |
| ForecastBench | 57.5 | — |
| HellaSwag | 84.8% | — |
| LiveBench | — | 46.9% |
| PIQA | 82.6% | — |
| WinoGrande | 82.3% | — |
Math Sonar leads
Qwen2.5 72B Instruct: 19.3 (#287), Sonar: 33.7 (#200)
| Benchmark | Qwen2.5 72B Instruct | Sonar |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.1% | — |
| Omni-MATH | 33% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1283 | — |
| MATH Level 5 | 63.2% | — |
Knowledge Not comparable
Qwen2.5 72B Instruct: 27.0 (#253), Sonar: —
| Benchmark | Qwen2.5 72B Instruct | Sonar |
|---|---|---|
| GPQA Diamond | 49.1% | — |
| MMLU-Pro | 63.1% | — |
| Confabulations | 19.1% | — |
| GPQA (HELM) | 42.6% | — |
| LMArena Expert | 1245 | — |
| ARC (AI2) Challenge | 94.5% | — |
| MMLU | 85.3% | — |
| TriviaQA | 71.9% | — |
Multilingual Not comparable
Qwen2.5 72B Instruct: 41.0 (#213), Sonar: —
| Benchmark | Qwen2.5 72B Instruct | Sonar |
|---|---|---|
| LMArena Non-English | 1252 | — |
| LMArena Chinese | 1272 | — |
| LMArena French | 1280 | — |
| LMArena German | 1234 | — |
| LMArena Japanese | 1180 | — |
| LMArena Korean | 1188 | — |
| LMArena Russian | 1264 | — |
| LMArena Spanish | 1256 | — |
Instruction Following Sonar leads
Qwen2.5 72B Instruct: 65.5 (#221), Sonar: 71.4 (#150)
| Benchmark | Qwen2.5 72B Instruct | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| IFEval | 80.6% | — |
| LMArena Instruction Following | 1254 | — |
Long Context Not comparable
Qwen2.5 72B Instruct: 38.9 (#188), Sonar: —
| Benchmark | Qwen2.5 72B Instruct | Sonar |
|---|---|---|
| LMArena Longer Query | 1282 | — |
Writing & Preference Sonar leads
Qwen2.5 72B Instruct: 46.7 (#215), Sonar: 52.6 (#167)
| Benchmark | Qwen2.5 72B Instruct | Sonar |
|---|---|---|
| LMArena Text | 1269 | — |
| LMArena Creative Writing | 1221 | — |
| WildBench | 80.2% | — |
| LMArena Multi-Turn | 1272 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Qwen2.5 72B Instruct better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 31.9 on the Noometry Index.
Which is cheaper, Qwen2.5 72B Instruct or Sonar?
Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is Qwen2.5 72B Instruct or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.7 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Qwen2.5 72B Instruct does, with 131K tokens against 128K.
How many benchmarks do Qwen2.5 72B Instruct and Sonar share?
0 benchmarks have published results for both models. Qwen2.5 72B Instruct has 43 scored results on Noometry and Sonar has 7.