# GLM-4.7 vs Qwen3.5-9B

> GLM-4.7 is the stronger model overall, scoring 41.7 to 33.3 on the Noometry Index. Qwen3.5-9B costs 8.9× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-4-7-vs-qwen3-5-9b
- Last updated: 2026-10-10
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. GLM-4.7 scores higher in 5 categories and Qwen3.5-9B in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GLM-4.7 leads 26.4 to 14.4.
- The biggest single-benchmark swing is Terminal-Bench: 33.4% for GLM-4.7 and 9.2% for Qwen3.5-9B.
- Qwen3.5-9B is cheaper at $0.10 / $0.15 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
- Qwen3.5-9B accepts more context: 262K tokens versus 205K.

## Snapshot

| | GLM-4.7 | Qwen3.5-9B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.7 | 33.3 |
| Rank | 117 | 235 |
| Context | 205K | 262K |
| Input $/M | $0.60 | $0.10 |
| Output $/M | $2.20 | $0.15 |
| Weights | Open | Open |

## Coding

- GLM-4.7: 43.6 (#74)
- Qwen3.5-9B: 35.3 (#213)

| Benchmark | GLM-4.7 | Qwen3.5-9B |
|---|---|---|
| SciCode | 45.1% | 27.5% |
| LMArena WebDev | 1435 | — |
| LMArena Coding | 1454 | — |
| ALE-Bench | 399.48 | — |

## Agentic & Tool Use

- GLM-4.7: 26.4 (#96)
- Qwen3.5-9B: 14.4 (#143)

| Benchmark | GLM-4.7 | Qwen3.5-9B |
|---|---|---|
| Terminal-Bench | 33.4% | 9.2% |
| Vending-Bench 2 | 2,377 | — |

## Reasoning

- GLM-4.7: 23.7 (#161)
- Qwen3.5-9B: 22.5 (#178)

| Benchmark | GLM-4.7 | Qwen3.5-9B |
|---|---|---|
| CritPt | 1.7% | 0.3% |
| Chess Puzzles | 6% | 12% |
| Epoch Capabilities Index | 143.53 | 139.45 |
| SimpleBench | 47.7% | — |
| LMArena Hard Prompts | 1443 | — |
| DTBench | — | 71.2% |
| LMCA | — | 24.5% |

## Math

- GLM-4.7: 37.7 (#92)
- Qwen3.5-9B: 33.5 (#174)

| Benchmark | GLM-4.7 | Qwen3.5-9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 61.7% |
| MathArena Final-Answer Competitions | — | 48.5% |
| ProofBench | 6% | — |
| LMArena Math | 1423 | — |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- GLM-4.7: 47.0 (#74)
- Qwen3.5-9B: 46.0 (#77)

| Benchmark | GLM-4.7 | Qwen3.5-9B |
|---|---|---|
| GPQA Diamond | 83.3% | 79% |
| SimpleQA Verified | 32.2% | — |
| Vectara Hallucination Rate | 11.7% | — |
| LMArena Expert | 1424 | — |

## Multilingual

- GLM-4.7: 53.0 (#75)
- Qwen3.5-9B: —

| Benchmark | GLM-4.7 | Qwen3.5-9B |
|---|---|---|
| LMArena Non-English | 1417 | — |
| LMArena Chinese | 1495 | — |
| LMArena French | 1432 | — |
| LMArena German | 1426 | — |
| LMArena Japanese | 1439 | — |
| LMArena Korean | 1401 | — |
| LMArena Russian | 1423 | — |
| LMArena Spanish | 1433 | — |

## Instruction Following

- GLM-4.7: 74.6 (#90)
- Qwen3.5-9B: —

| Benchmark | GLM-4.7 | Qwen3.5-9B |
|---|---|---|
| LMArena Instruction Following | 1411 | — |

## Long Context

- GLM-4.7: 42.8 (#111)
- Qwen3.5-9B: —

| Benchmark | GLM-4.7 | Qwen3.5-9B |
|---|---|---|
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
| LMArena Longer Query | 1432 | — |

## Writing & Preference

- GLM-4.7: 61.1 (#89)
- Qwen3.5-9B: —

| Benchmark | GLM-4.7 | Qwen3.5-9B |
|---|---|---|
| LMArena Text | 1436 | — |
| LMArena Creative Writing | 1401 | — |
| EQ-Bench Creative Writing | 1413 | — |
| LMArena Multi-Turn | 1446 | — |

## FAQ

### Is GLM-4.7 better than Qwen3.5-9B?

GLM-4.7 is the stronger model overall, scoring 41.7 to 33.3 on the Noometry Index. Qwen3.5-9B costs 8.9× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.

### Which is cheaper, GLM-4.7 or Qwen3.5-9B?

Qwen3.5-9B is cheaper. It lists at $0.10 per million input tokens and $0.15 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

### Is GLM-4.7 or Qwen3.5-9B better for coding?

GLM-4.7 scores higher on coding benchmarks: 43.6 versus 35.3 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.5-9B does, with 262K tokens against 205K.

### How many benchmarks do GLM-4.7 and Qwen3.5-9B share?

7 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Qwen3.5-9B has 10.