# GLM-4.6 vs Qwen1.5-72B

> GLM-4.6 is the stronger model overall, scoring 41.4 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-6-vs-qwen1-5-72b
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GLM-4.6 scores higher in 8 categories and Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.6 leads 40.2 to 11.5.

## Snapshot

| | GLM-4.6 | Qwen1.5-72B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.4 | 30.8 |
| Rank | 135 | 285 |
| Context | 205K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.20 | — |
| Weights | Open | Open |

## Coding

- GLM-4.6: 40.1 (#148)
- Qwen1.5-72B: 31.9 (#277)

| Benchmark | GLM-4.6 | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1449 | 1165 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1340 | — |
| SciCode | 38.4% | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| ALE-Bench | 340.82 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |

## Agentic & Tool Use

- GLM-4.6: 32.3 (#66)
- Qwen1.5-72B: —

| Benchmark | GLM-4.6 | Qwen1.5-72B |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |

## Reasoning

- GLM-4.6: 23.7 (#172)
- Qwen1.5-72B: 22.2 (#203)

| Benchmark | GLM-4.6 | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1148 |
| Kagi LLM Benchmark | 47.4% | — |
| CritPt | 1.1% | — |

## Math

- GLM-4.6: 39.1 (#111)
- Qwen1.5-72B: 33.2 (#205)

| Benchmark | GLM-4.6 | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1432 | 1164 |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-4.6: 40.2 (#124)
- Qwen1.5-72B: 11.5 (#300)

| Benchmark | GLM-4.6 | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1431 | 1136 |
| GPQA Diamond | — | 28.8% |
| Vectara Hallucination Rate | 9.5% | — |

## Multilingual

- GLM-4.6: 53.5 (#66)
- Qwen1.5-72B: 33.2 (#253)

| Benchmark | GLM-4.6 | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1426 | 1135 |
| LMArena Chinese | 1499 | 1186 |
| LMArena French | 1459 | 1159 |
| LMArena German | 1447 | 1084 |
| LMArena Japanese | 1393 | 1061 |
| LMArena Korean | 1400 | 1050 |
| LMArena Russian | 1419 | 1104 |
| LMArena Spanish | 1436 | 1110 |

## Instruction Following

- GLM-4.6: 74.3 (#98)
- Qwen1.5-72B: 59.3 (#256)

| Benchmark | GLM-4.6 | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1410 | 1141 |

## Long Context

- GLM-4.6: 43.4 (#94)
- Qwen1.5-72B: 35.1 (#243)

| Benchmark | GLM-4.6 | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1422 | 1157 |

## Writing & Preference

- GLM-4.6: 61.1 (#90)
- Qwen1.5-72B: 37.3 (#258)

| Benchmark | GLM-4.6 | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1440 | 1166 |
| LMArena Creative Writing | 1411 | 1137 |
| LMArena Multi-Turn | 1427 | 1160 |
| EQ-Bench Creative Writing | 1411 | — |

## FAQ

### Is GLM-4.6 better than Qwen1.5-72B?

GLM-4.6 is the stronger model overall, scoring 41.4 to 30.8 on the Noometry Index.

### Is GLM-4.6 or Qwen1.5-72B better for coding?

GLM-4.6 scores higher on coding benchmarks: 40.1 versus 31.9 in the Noometry coding category.

### How many benchmarks do GLM-4.6 and Qwen1.5-72B share?

17 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Qwen1.5-72B has 22.