# Qwen2-72B vs Qwen3.7 Plus

> Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-72b-vs-qwen3-7-plus
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Qwen2-72B scores higher in 0 categories and Qwen3.7 Plus in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Plus leads 54.9 to 21.2.
- The biggest single-benchmark swing is GPQA Diamond: 40.8% for Qwen2-72B and 87.9% for Qwen3.7 Plus.
- Qwen2-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen2-72B | Qwen3.7 Plus |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 29.5 | 45.0 |
| Rank | 294 | 66 |
| Context | — | 1M |
| Input $/M | — | $0.40 |
| Output $/M | — | $1.60 |
| Weights | Open | Proprietary |

## Coding

- Qwen2-72B: 28.7 (#303)
- Qwen3.7 Plus: 36.1 (#200)

| Benchmark | Qwen2-72B | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1196 | 1473 |
| FrontierCode | — | 10.2% |
| SciCode | — | 45.5% |
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| BigCodeBench Complete | 54% | — |

## Agentic & Tool Use

- Qwen2-72B: 16.9 (#138)
- Qwen3.7 Plus: 21.2 (#130)

| Benchmark | Qwen2-72B | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |

## Reasoning

- Qwen2-72B: 22.2 (#184)
- Qwen3.7 Plus: 38.4 (#54)

| Benchmark | Qwen2-72B | Qwen3.7 Plus |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1460 |
| Epoch Capabilities Index | 125.27 | 147.39 |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |

## Math

- Qwen2-72B: 27.9 (#232)
- Qwen3.7 Plus: 49.3 (#47)

| Benchmark | Qwen2-72B | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1235 | 1467 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| MATH Level 5 | 39.1% | — |

## Knowledge

- Qwen2-72B: 21.2 (#270)
- Qwen3.7 Plus: 54.9 (#46)

| Benchmark | Qwen2-72B | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 40.8% | 87.9% |
| LMArena Expert | 1171 | 1467 |
| MMLU | 82.4% | — |

## Multimodal

- Qwen2-72B: —
- Qwen3.7 Plus: 41.2 (#30)

| Benchmark | Qwen2-72B | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1281 |
| LMArena Document | — | 1444 |

## Multilingual

- Qwen2-72B: 36.0 (#239)
- Qwen3.7 Plus: 55.0 (#36)

| Benchmark | Qwen2-72B | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1176 | 1445 |
| LMArena Chinese | 1240 | 1510 |
| LMArena French | 1169 | 1471 |
| LMArena German | 1151 | 1471 |
| LMArena Japanese | 1111 | 1411 |
| LMArena Korean | 1083 | 1416 |
| LMArena Russian | 1169 | 1457 |
| LMArena Spanish | 1168 | 1453 |

## Instruction Following

- Qwen2-72B: 62.0 (#236)
- Qwen3.7 Plus: 75.9 (#49)

| Benchmark | Qwen2-72B | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1181 | 1439 |

## Long Context

- Qwen2-72B: 36.1 (#230)
- Qwen3.7 Plus: 44.5 (#61)

| Benchmark | Qwen2-72B | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1193 | 1454 |

## Writing & Preference

- Qwen2-72B: 41.0 (#236)
- Qwen3.7 Plus: 64.5 (#54)

| Benchmark | Qwen2-72B | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1203 | 1454 |
| LMArena Creative Writing | 1181 | 1439 |
| LMArena Multi-Turn | 1195 | 1459 |

## FAQ

### Is Qwen2-72B better than Qwen3.7 Plus?

Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 29.5 on the Noometry Index.

### Is Qwen2-72B or Qwen3.7 Plus better for coding?

Qwen3.7 Plus scores higher on coding benchmarks: 36.1 versus 28.7 in the Noometry coding category.

### How many benchmarks do Qwen2-72B and Qwen3.7 Plus share?

19 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Qwen3.7 Plus has 32.