# Qwen2-72B vs Qwen3.5-9B

> Qwen3.5-9B is the stronger model overall, scoring 33.8 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-72b-vs-qwen3-5-9b
- Last updated: 2026-10-12
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Qwen2-72B scores higher in 2 categories and Qwen3.5-9B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5-9B leads 46.0 to 21.2.
- The biggest single-benchmark swing is GPQA Diamond: 40.8% for Qwen2-72B and 79% for Qwen3.5-9B.

## Snapshot

| | Qwen2-72B | Qwen3.5-9B |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.0 | 33.8 |
| Rank | 300 | 236 |
| Context | — | 262K |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.15 |
| Weights | Open | Open |

## Coding

- Qwen2-72B: 29.1 (#310)
- Qwen3.5-9B: 35.9 (#217)

| Benchmark | Qwen2-72B | Qwen3.5-9B |
|---|---|---|
| SciCode | — | 27.5% |
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| LMArena Coding | 1196 | — |
| BigCodeBench Complete | 54% | — |

## Agentic & Tool Use

- Qwen2-72B: 17.0 (#146)
- Qwen3.5-9B: 14.5 (#151)

| Benchmark | Qwen2-72B | Qwen3.5-9B |
|---|---|---|
| Terminal-Bench | — | 9.2% |
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |

## Reasoning

- Qwen2-72B: 23.2 (#181)
- Qwen3.5-9B: 23.1 (#182)

| Benchmark | Qwen2-72B | Qwen3.5-9B |
|---|---|---|
| Epoch Capabilities Index | 125.28 | 139.46 |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 12% |
| LMArena Hard Prompts | 1191 | — |
| DTBench | — | 71.2% |
| LMCA | — | 24.5% |

## Math

- Qwen2-72B: 30.2 (#236)
- Qwen3.5-9B: 34.8 (#192)

| Benchmark | Qwen2-72B | Qwen3.5-9B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 48.5% |
| OTIS Mock AIME 2024-2025 | — | 61.7% |
| LMArena Math | 1235 | — |
| MATH Level 5 | 39.1% | — |

## Knowledge

- Qwen2-72B: 21.2 (#275)
- Qwen3.5-9B: 46.0 (#84)

| Benchmark | Qwen2-72B | Qwen3.5-9B |
|---|---|---|
| GPQA Diamond | 40.8% | 79% |
| LMArena Expert | 1171 | — |
| MMLU | 82.4% | — |

## Multilingual

- Qwen2-72B: 35.9 (#244)
- Qwen3.5-9B: —

| Benchmark | Qwen2-72B | Qwen3.5-9B |
|---|---|---|
| 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)
- Qwen3.5-9B: —

| Benchmark | Qwen2-72B | Qwen3.5-9B |
|---|---|---|
| LMArena Instruction Following | 1181 | — |

## Long Context

- Qwen2-72B: 36.1 (#235)
- Qwen3.5-9B: —

| Benchmark | Qwen2-72B | Qwen3.5-9B |
|---|---|---|
| LMArena Longer Query | 1192 | — |

## Writing & Preference

- Qwen2-72B: 40.8 (#241)
- Qwen3.5-9B: —

| Benchmark | Qwen2-72B | Qwen3.5-9B |
|---|---|---|
| LMArena Text | 1203 | — |
| LMArena Creative Writing | 1181 | — |
| LMArena Multi-Turn | 1196 | — |

## FAQ

### Is Qwen2-72B better than Qwen3.5-9B?

Qwen3.5-9B is the stronger model overall, scoring 33.8 to 30.0 on the Noometry Index.

### Is Qwen2-72B or Qwen3.5-9B better for coding?

Qwen3.5-9B scores higher on coding benchmarks: 35.9 versus 29.1 in the Noometry coding category.

### How many benchmarks do Qwen2-72B and Qwen3.5-9B share?

2 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Qwen3.5-9B has 10.