# Qwen2-72B vs Sonar

> Sonar is the stronger model overall, scoring 38.5 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-72b-vs-sonar
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in writing & preference, where Sonar leads 52.6 to 40.8.
- Qwen2-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen2-72B | Sonar |
|---|---|---|
| Provider | Alibaba (Qwen) | Perplexity |
| Noometry Index | 30.0 | 38.5 |
| Rank | 300 | 187 |
| Context | — | 128K |
| Input $/M | — | $1 |
| Output $/M | — | $1 |
| Weights | Open | Proprietary |

## Coding

- Qwen2-72B: 29.1 (#310)
- Sonar: 35.7 (#221)

| Benchmark | Qwen2-72B | Sonar |
|---|---|---|
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1196 | — |
| BigCodeBench Complete | 54% | — |

## Agentic & Tool Use

- Qwen2-72B: 17.0 (#146)
- Sonar: —

| Benchmark | Qwen2-72B | Sonar |
|---|---|---|
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |

## Reasoning

- Qwen2-72B: 23.2 (#181)
- Sonar: 21.1 (#227)

| Benchmark | Qwen2-72B | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1191 | — |
| LiveBench Data Analysis | — | 37.9% |
| Epoch Capabilities Index | 125.28 | — |
| LiveBench | — | 46.9% |

## Math

- Qwen2-72B: 30.2 (#236)
- Sonar: 33.7 (#200)

| Benchmark | Qwen2-72B | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1235 | — |
| MATH Level 5 | 39.1% | — |

## Knowledge

- Qwen2-72B: 21.2 (#275)
- Sonar: —

| Benchmark | Qwen2-72B | Sonar |
|---|---|---|
| GPQA Diamond | 40.8% | — |
| LMArena Expert | 1171 | — |
| MMLU | 82.4% | — |

## Multilingual

- Qwen2-72B: 35.9 (#244)
- Sonar: —

| Benchmark | Qwen2-72B | Sonar |
|---|---|---|
| LMArena Non-English | 1176 | — |
| LMArena Chinese | 1240 | — |
| LMArena French | 1170 | — |
| LMArena German | 1151 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1083 | — |
| LMArena Russian | 1169 | — |
| LMArena Spanish | 1169 | — |

## Instruction Following

- Qwen2-72B: 61.7 (#241)
- Sonar: 71.4 (#150)

| Benchmark | Qwen2-72B | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1181 | — |

## Long Context

- Qwen2-72B: 36.1 (#235)
- Sonar: —

| Benchmark | Qwen2-72B | Sonar |
|---|---|---|
| LMArena Longer Query | 1192 | — |

## Writing & Preference

- Qwen2-72B: 40.8 (#241)
- Sonar: 52.6 (#167)

| Benchmark | Qwen2-72B | Sonar |
|---|---|---|
| LMArena Text | 1203 | — |
| LMArena Creative Writing | 1181 | — |
| LMArena Multi-Turn | 1196 | — |
| LiveBench Language | — | 44.1% |

## FAQ

### Is Qwen2-72B better than Sonar?

Sonar is the stronger model overall, scoring 38.5 to 30.0 on the Noometry Index.

### Is Qwen2-72B or Sonar better for coding?

Sonar scores higher on coding benchmarks: 35.7 versus 29.1 in the Noometry coding category.

### How many benchmarks do Qwen2-72B and Sonar share?

0 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Sonar has 7.