# GLM-4.7-Flash vs Qwen2-72B

> GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-7-flash-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GLM-4.7-Flash scores higher in 7 categories and Qwen2-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.7-Flash leads 35.4 to 21.2.
- The biggest single-benchmark swing is GPQA Diamond: 60.5% for GLM-4.7-Flash and 40.8% for Qwen2-72B.

## Snapshot

| | GLM-4.7-Flash | Qwen2-72B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 38.4 | 29.5 |
| Rank | 175 | 294 |
| Context | 200K | — |
| Input $/M | $0.06 | — |
| Output $/M | $0.40 | — |
| Weights | Open | Open |

## Coding

- GLM-4.7-Flash: 40.0 (#133)
- Qwen2-72B: 28.7 (#303)

| Benchmark | GLM-4.7-Flash | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1383 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- GLM-4.7-Flash: —
- Qwen2-72B: 16.9 (#138)

| Benchmark | GLM-4.7-Flash | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- GLM-4.7-Flash: 20.2 (#224)
- Qwen2-72B: 22.2 (#184)

| Benchmark | GLM-4.7-Flash | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1356 | 1191 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | — | 125.27 |

## Math

- GLM-4.7-Flash: 34.4 (#159)
- Qwen2-72B: 27.9 (#232)

| Benchmark | GLM-4.7-Flash | Qwen2-72B |
|---|---|---|
| LMArena Math | 1354 | 1235 |
| OTIS Mock AIME 2024-2025 | 58.3% | — |
| MATH Level 5 | — | 39.1% |

## Knowledge

- GLM-4.7-Flash: 35.4 (#177)
- Qwen2-72B: 21.2 (#270)

| Benchmark | GLM-4.7-Flash | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 60.5% | 40.8% |
| LMArena Expert | 1357 | 1171 |
| Vectara Hallucination Rate | 9.3% | — |
| MMLU | — | 82.4% |

## Multilingual

- GLM-4.7-Flash: 46.8 (#152)
- Qwen2-72B: 36.0 (#239)

| Benchmark | GLM-4.7-Flash | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1331 | 1176 |
| LMArena Chinese | 1403 | 1240 |
| LMArena French | 1332 | 1169 |
| LMArena German | 1336 | 1151 |
| LMArena Korean | 1284 | 1083 |
| LMArena Russian | 1333 | 1169 |
| LMArena Spanish | 1351 | 1168 |
| LMArena Japanese | — | 1111 |

## Instruction Following

- GLM-4.7-Flash: 70.3 (#162)
- Qwen2-72B: 62.0 (#236)

| Benchmark | GLM-4.7-Flash | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1327 | 1181 |

## Long Context

- GLM-4.7-Flash: 40.9 (#143)
- Qwen2-72B: 36.1 (#230)

| Benchmark | GLM-4.7-Flash | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1345 | 1193 |

## Writing & Preference

- GLM-4.7-Flash: 47.7 (#206)
- Qwen2-72B: 41.0 (#236)

| Benchmark | GLM-4.7-Flash | Qwen2-72B |
|---|---|---|
| LMArena Text | 1351 | 1203 |
| LMArena Creative Writing | 1297 | 1181 |
| LMArena Multi-Turn | 1342 | 1195 |
| EQ-Bench Creative Writing | 1125 | — |

## FAQ

### Is GLM-4.7-Flash better than Qwen2-72B?

GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 29.5 on the Noometry Index.

### Is GLM-4.7-Flash or Qwen2-72B better for coding?

GLM-4.7-Flash scores higher on coding benchmarks: 40.0 versus 28.7 in the Noometry coding category.

### How many benchmarks do GLM-4.7-Flash and Qwen2-72B share?

17 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and Qwen2-72B has 26.