# GLM-4.7 vs Qwen2.5 7B Instruct

> GLM-4.7 is the stronger model overall, scoring 41.7 to 28.6 on the Noometry Index. Qwen2.5 7B Instruct costs 3.3× 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-qwen2-5-7b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. GLM-4.7 scores higher in 7 categories and Qwen2.5 7B Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 17.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 2.5% for Qwen2.5 7B Instruct.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
- GLM-4.7 accepts more context: 205K tokens versus 131K.

## Snapshot

| | GLM-4.7 | Qwen2.5 7B Instruct |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.7 | 28.6 |
| Rank | 117 | 314 |
| Context | 205K | 131K |
| Input $/M | $0.60 | $0.17 |
| Output $/M | $2.20 | $0.70 |
| Weights | Open | Open |

## Coding

- GLM-4.7: 43.6 (#74)
- Qwen2.5 7B Instruct: 35.9 (#204)

| Benchmark | GLM-4.7 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1454 | — |
| BigCodeBench Complete | — | 46.1% |
| ALE-Bench | 399.48 | — |

## Agentic & Tool Use

- GLM-4.7: 26.4 (#96)
- Qwen2.5 7B Instruct: 23.5 (#117)

| Benchmark | GLM-4.7 | Qwen2.5 7B Instruct |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| BALROG | — | 7.8% |
| Vending-Bench 2 | 2,377 | — |

## Reasoning

- GLM-4.7: 23.7 (#161)
- Qwen2.5 7B Instruct: 14.3 (#317)

| Benchmark | GLM-4.7 | Qwen2.5 7B Instruct |
|---|---|---|
| Chess Puzzles | 6% | 0% |
| Epoch Capabilities Index | 143.53 | 118.44 |
| SimpleBench | 47.7% | — |
| CritPt | 1.7% | — |
| LMArena Hard Prompts | 1443 | — |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |

## Math

- GLM-4.7: 37.7 (#92)
- Qwen2.5 7B Instruct: 11.8 (#300)

| Benchmark | GLM-4.7 | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 2.5% |
| ProofBench | 6% | — |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1423 | — |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- GLM-4.7: 47.0 (#74)
- Qwen2.5 7B Instruct: 17.0 (#281)

| Benchmark | GLM-4.7 | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 83.3% | 35.5% |
| SimpleQA Verified | 32.2% | — |
| MMLU-Pro | — | 53.9% |
| Vectara Hallucination Rate | 11.7% | — |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1424 | — |
| MMLU | — | 72.9% |

## Multilingual

- GLM-4.7: 53.0 (#75)
- Qwen2.5 7B Instruct: —

| Benchmark | GLM-4.7 | Qwen2.5 7B Instruct |
|---|---|---|
| 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)
- Qwen2.5 7B Instruct: 63.4 (#226)

| Benchmark | GLM-4.7 | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1411 | — |

## Long Context

- GLM-4.7: 42.8 (#111)
- Qwen2.5 7B Instruct: —

| Benchmark | GLM-4.7 | Qwen2.5 7B Instruct |
|---|---|---|
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
| LMArena Longer Query | 1432 | — |

## Writing & Preference

- GLM-4.7: 61.1 (#89)
- Qwen2.5 7B Instruct: 48.8 (#194)

| Benchmark | GLM-4.7 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1436 | — |
| LMArena Creative Writing | 1401 | — |
| EQ-Bench Creative Writing | 1413 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1446 | — |

## FAQ

### Is GLM-4.7 better than Qwen2.5 7B Instruct?

GLM-4.7 is the stronger model overall, scoring 41.7 to 28.6 on the Noometry Index. Qwen2.5 7B Instruct costs 3.3× 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 Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

### Is GLM-4.7 or Qwen2.5 7B Instruct better for coding?

GLM-4.7 scores higher on coding benchmarks: 43.6 versus 35.9 in the Noometry coding category.

### Which has the bigger context window?

GLM-4.7 does, with 205K tokens against 131K.

### How many benchmarks do GLM-4.7 and Qwen2.5 7B Instruct share?

4 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Qwen2.5 7B Instruct has 15.