# GLM-4.5-Air vs GLM-4.7

> GLM-4.7 is the stronger model overall, scoring 42.0 to 38.9 on the Noometry Index. GLM-4.5-Air costs 2.4× 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-4-5-air-vs-glm-4-7
- Last updated: 2026-10-12
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GLM-4.5-Air scores higher in 0 categories and GLM-4.7 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 35.0.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 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-4.5-Air | GLM-4.7 |
|---|---|---|
| Provider | Z.ai (Zhipu) | Z.ai (Zhipu) |
| Noometry Index | 38.9 | 42.0 |
| Rank | 177 | 124 |
| Context | 131K | 205K |
| Input $/M | $0.20 | $0.60 |
| Output $/M | $1.10 | $2.20 |
| Weights | Open | Open |

## Coding

- GLM-4.5-Air: 33.3 (#259)
- GLM-4.7: 44.0 (#79)

| Benchmark | GLM-4.5-Air | GLM-4.7 |
|---|---|---|
| LMArena Coding | 1397 | 1454 |
| LMArena WebDev | — | 1435 |
| SciCode | — | 45.1% |
| GSO | 2.9% | — |
| ALE-Bench | — | 399.48 |

## Agentic & Tool Use

- GLM-4.5-Air: —
- GLM-4.7: 26.5 (#103)

| Benchmark | GLM-4.5-Air | GLM-4.7 |
|---|---|---|
| Terminal-Bench | — | 33.4% |
| Vending-Bench 2 | — | 2,377 |

## Reasoning

- GLM-4.5-Air: 24.1 (#166)
- GLM-4.7: 24.3 (#164)

| Benchmark | GLM-4.5-Air | GLM-4.7 |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1443 |
| SimpleBench | — | 47.7% |
| Kagi LLM Benchmark | 43% | — |
| CritPt | — | 1.7% |
| Chess Puzzles | — | 6% |
| Epoch Capabilities Index | — | 143.51 |
| ForecastBench | 59.2 | — |

## Math

- GLM-4.5-Air: 36.2 (#170)
- GLM-4.7: 38.6 (#135)

| Benchmark | GLM-4.5-Air | GLM-4.7 |
|---|---|---|
| LMArena Math | 1396 | 1423 |
| OTIS Mock AIME 2024-2025 | — | 83.3% |
| ProofBench | — | 6% |
| Omni-MATH | 39.1% | — |
| FrontierMath (Feb 2025 set) | — | 2.4% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- GLM-4.5-Air: 35.0 (#191)
- GLM-4.7: 47.0 (#80)

| Benchmark | GLM-4.5-Air | GLM-4.7 |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 11.7% |
| LMArena Expert | 1370 | 1424 |
| GPQA Diamond | — | 83.3% |
| Humanity's Last Exam | 8.1% | — |
| SimpleQA Verified | — | 32.2% |
| MMLU-Pro | 76.2% | — |
| GPQA (HELM) | 59.4% | — |

## Multilingual

- GLM-4.5-Air: 49.1 (#135)
- GLM-4.7: 52.8 (#79)

| Benchmark | GLM-4.5-Air | GLM-4.7 |
|---|---|---|
| LMArena Non-English | 1366 | 1417 |
| LMArena Chinese | 1426 | 1495 |
| LMArena French | 1399 | 1432 |
| LMArena German | 1377 | 1424 |
| LMArena Japanese | 1348 | 1439 |
| LMArena Korean | 1308 | 1399 |
| LMArena Russian | 1373 | 1423 |
| LMArena Spanish | 1386 | 1434 |

## Instruction Following

- GLM-4.5-Air: 69.6 (#171)
- GLM-4.7: 74.4 (#95)

| Benchmark | GLM-4.5-Air | GLM-4.7 |
|---|---|---|
| LMArena Instruction Following | 1354 | 1411 |
| IFEval | 81.2% | — |

## Long Context

- GLM-4.5-Air: 41.6 (#135)
- GLM-4.7: 42.8 (#116)

| Benchmark | GLM-4.5-Air | GLM-4.7 |
|---|---|---|
| LMArena Longer Query | 1366 | 1432 |
| CL-bench | — | 15.9% |
| CL-bench Life | — | 10.9% |

## Writing & Preference

- GLM-4.5-Air: 55.9 (#139)
- GLM-4.7: 60.9 (#93)

| Benchmark | GLM-4.5-Air | GLM-4.7 |
|---|---|---|
| LMArena Text | 1384 | 1435 |
| LMArena Creative Writing | 1343 | 1401 |
| LMArena Multi-Turn | 1371 | 1446 |
| EQ-Bench Creative Writing | — | 1413 |
| WildBench | 78.9% | — |

## FAQ

### Is GLM-4.5-Air better than GLM-4.7?

GLM-4.7 is the stronger model overall, scoring 42.0 to 38.9 on the Noometry Index. GLM-4.5-Air costs 2.4× 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-4.5-Air or GLM-4.7?

GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

### Is GLM-4.5-Air or GLM-4.7 better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 33.3 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-4.5-Air and GLM-4.7 share?

18 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and GLM-4.7 has 36.