# Command A vs GLM-4.5-Air

> GLM-4.5-Air is the stronger model overall, scoring 38.9 to 36.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/command-a-vs-glm-4-5-air
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Command A scores higher in 1 category and GLM-4.5-Air in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5-Air leads 55.9 to 47.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 28.8% for Command A and 43% for GLM-4.5-Air.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $2.50 / $10 for Command A.
- Command A accepts more context: 256K tokens versus 131K.

## Snapshot

| | Command A | GLM-4.5-Air |
|---|---|---|
| Provider | Cohere | Z.ai (Zhipu) |
| Noometry Index | 36.5 | 38.9 |
| Rank | 215 | 177 |
| Context | 256K | 131K |
| Input $/M | $2.50 | $0.20 |
| Output $/M | $10 | $1.10 |
| Weights | Open | Open |

## Coding

- Command A: 27.2 (#322)
- GLM-4.5-Air: 33.3 (#259)

| Benchmark | Command A | GLM-4.5-Air |
|---|---|---|
| LMArena Coding | 1330 | 1397 |
| Aider Polyglot | 12% | — |
| GSO | — | 2.9% |

## Agentic & Tool Use

- Command A: 35.9 (#40)
- GLM-4.5-Air: —

| Benchmark | Command A | GLM-4.5-Air |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |

## Reasoning

- Command A: 18.3 (#283)
- GLM-4.5-Air: 24.1 (#166)

| Benchmark | Command A | GLM-4.5-Air |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 43% |
| LMArena Hard Prompts | 1326 | 1379 |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
| ForecastBench | — | 59.2 |

## Math

- Command A: 36.2 (#171)
- GLM-4.5-Air: 36.2 (#170)

| Benchmark | Command A | GLM-4.5-Air |
|---|---|---|
| LMArena Math | 1300 | 1396 |
| Omni-MATH | — | 39.1% |

## Knowledge

- Command A: 37.1 (#159)
- GLM-4.5-Air: 35.0 (#191)

| Benchmark | Command A | GLM-4.5-Air |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 9.3% |
| LMArena Expert | 1295 | 1370 |
| Humanity's Last Exam | — | 8.1% |
| MMLU-Pro | — | 76.2% |
| GPQA (HELM) | — | 59.4% |

## Multilingual

- Command A: 45.3 (#170)
- GLM-4.5-Air: 49.1 (#135)

| Benchmark | Command A | GLM-4.5-Air |
|---|---|---|
| LMArena Non-English | 1313 | 1366 |
| LMArena Chinese | 1327 | 1426 |
| LMArena French | 1351 | 1399 |
| LMArena German | 1341 | 1377 |
| LMArena Japanese | 1285 | 1348 |
| LMArena Korean | 1285 | 1308 |
| LMArena Russian | 1314 | 1373 |
| LMArena Spanish | 1347 | 1386 |

## Instruction Following

- Command A: 69.1 (#177)
- GLM-4.5-Air: 69.6 (#171)

| Benchmark | Command A | GLM-4.5-Air |
|---|---|---|
| LMArena Instruction Following | 1309 | 1354 |
| IFEval | — | 81.2% |

## Long Context

- Command A: 40.6 (#151)
- GLM-4.5-Air: 41.6 (#135)

| Benchmark | Command A | GLM-4.5-Air |
|---|---|---|
| LMArena Longer Query | 1334 | 1366 |

## Writing & Preference

- Command A: 47.6 (#208)
- GLM-4.5-Air: 55.9 (#139)

| Benchmark | Command A | GLM-4.5-Air |
|---|---|---|
| LMArena Text | 1331 | 1384 |
| LMArena Creative Writing | 1319 | 1343 |
| LMArena Multi-Turn | 1339 | 1371 |
| EQ-Bench Creative Writing | 1145 | — |
| WildBench | — | 78.9% |

## FAQ

### Is Command A better than GLM-4.5-Air?

GLM-4.5-Air is the stronger model overall, scoring 38.9 to 36.5 on the Noometry Index.

### Which is cheaper, Command A or GLM-4.5-Air?

GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; Command A lists at $2.50 and $10.

### Is Command A or GLM-4.5-Air better for coding?

GLM-4.5-Air scores higher on coding benchmarks: 33.3 versus 27.2 in the Noometry coding category.

### Which has the bigger context window?

Command A does, with 256K tokens against 131K.

### How many benchmarks do Command A and GLM-4.5-Air share?

19 benchmarks have published results for both models. Command A has 24 scored results on Noometry and GLM-4.5-Air has 27.