# Qwen Plus vs Qwen2-72B

> Qwen Plus is the stronger model overall, scoring 37.1 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen-plus-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Qwen Plus scores higher in 7 categories and Qwen2-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Plus leads 52.2 to 40.8.
- The biggest single-benchmark swing is MATH Level 5: 65.3% for Qwen Plus and 39.1% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen Plus | Qwen2-72B |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 37.1 | 30.0 |
| Rank | 210 | 300 |
| Context | 1M | — |
| Input $/M | $0.40 | — |
| Output $/M | $1.20 | — |
| Weights | Proprietary | Open |

## Coding

- Qwen Plus: 38.9 (#167)
- Qwen2-72B: 29.1 (#310)

| Benchmark | Qwen Plus | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1328 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- Qwen Plus: —
- Qwen2-72B: 17.0 (#146)

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

## Reasoning

- Qwen Plus: 28.4 (#107)
- Qwen2-72B: 23.2 (#181)

| Benchmark | Qwen Plus | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1317 | 1191 |
| Kagi LLM Benchmark | 63.3% | — |
| DTBench | 81.1% | — |
| LMCA | 24% | — |
| Epoch Capabilities Index | — | 125.28 |

## Math

- Qwen Plus: 23.3 (#271)
- Qwen2-72B: 30.2 (#236)

| Benchmark | Qwen Plus | Qwen2-72B |
|---|---|---|
| LMArena Math | 1326 | 1235 |
| MATH Level 5 | 65.3% | 39.1% |
| OTIS Mock AIME 2024-2025 | 17.8% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |

## Knowledge

- Qwen Plus: 27.4 (#251)
- Qwen2-72B: 21.2 (#275)

| Benchmark | Qwen Plus | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 48.1% | 40.8% |
| LMArena Expert | 1328 | 1171 |
| MMLU | — | 82.4% |

## Multilingual

- Qwen Plus: 45.1 (#175)
- Qwen2-72B: 35.9 (#244)

| Benchmark | Qwen Plus | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1310 | 1176 |
| LMArena Chinese | 1347 | 1240 |
| LMArena Japanese | 1251 | 1111 |
| LMArena Russian | 1323 | 1169 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Korean | — | 1083 |
| LMArena Spanish | — | 1169 |

## Instruction Following

- Qwen Plus: 68.8 (#181)
- Qwen2-72B: 61.7 (#241)

| Benchmark | Qwen Plus | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1303 | 1181 |

## Long Context

- Qwen Plus: 40.3 (#158)
- Qwen2-72B: 36.1 (#235)

| Benchmark | Qwen Plus | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1324 | 1192 |

## Writing & Preference

- Qwen Plus: 52.2 (#176)
- Qwen2-72B: 40.8 (#241)

| Benchmark | Qwen Plus | Qwen2-72B |
|---|---|---|
| LMArena Text | 1326 | 1203 |
| LMArena Creative Writing | 1293 | 1181 |
| LMArena Multi-Turn | 1336 | 1196 |

## FAQ

### Is Qwen Plus better than Qwen2-72B?

Qwen Plus is the stronger model overall, scoring 37.1 to 30.0 on the Noometry Index.

### Is Qwen Plus or Qwen2-72B better for coding?

Qwen Plus scores higher on coding benchmarks: 38.9 versus 29.1 in the Noometry coding category.

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

15 benchmarks have published results for both models. Qwen Plus has 20 scored results on Noometry and Qwen2-72B has 26.