# Command A vs GLM-5.2

> GLM-5.2 is the stronger model overall, scoring 50.9 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/command-a-vs-glm-5-2
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Command A scores higher in 1 category and GLM-5.2 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.2 leads 42.1 to 17.7.
- The biggest single-benchmark swing is LMCA: 10.3% for Command A and 45.8% for GLM-5.2.
- GLM-5.2 is cheaper at $1.40 / $4.40 per million input/output tokens, against $2.50 / $10 for Command A.
- GLM-5.2 accepts more context: 1M tokens versus 256K.

## Snapshot

| | Command A | GLM-5.2 |
|---|---|---|
| Provider | Cohere | Z.ai (Zhipu) |
| Noometry Index | 35.9 | 50.9 |
| Rank | 212 | 38 |
| Context | 256K | 1M |
| Input $/M | $2.50 | $1.40 |
| Output $/M | $10 | $4.40 |
| Weights | Open | Open |

## Coding

- Command A: 26.8 (#317)
- GLM-5.2: 50.9 (#37)

| Benchmark | Command A | GLM-5.2 |
|---|---|---|
| LMArena Coding | 1331 | 1484 |
| SWE-bench Verified | — | 78.7% |
| DeepSWE | — | 43.8% |
| FrontierCode | — | 24.5% |
| Aider Polyglot | 12% | — |
| LMArena WebDev | — | 1604 |
| SciCode | — | 50.5% |
| WeirdML | — | 70.1% |
| ALE-Bench | — | 1,047 |

## Agentic & Tool Use

- Command A: 35.7 (#36)
- GLM-5.2: 31.6 (#63)

| Benchmark | Command A | GLM-5.2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 31.7% |
| GBAEval | — | 0% |
| Vending-Bench 2 | — | 8,314 |

## Reasoning

- Command A: 17.7 (#276)
- GLM-5.2: 42.1 (#46)

| Benchmark | Command A | GLM-5.2 |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 62.6% |
| LMArena Hard Prompts | 1326 | 1480 |
| DTBench | 61.3% | 93.6% |
| LMCA | 10.3% | 45.8% |
| ARC-AGI-2 | — | 22.8% |
| SimpleBench | — | 58.8% |
| NYT Connections (extended) | — | 74.3% |
| ARC-AGI-1 | — | 77% |
| CritPt | — | 20.9% |
| Chess Puzzles | — | 21% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 19% |
| Surface Evolver Bench | — | 55.6% |
| Epoch Capabilities Index | — | 151.76 |

## Math

- Command A: 33.5 (#172)
- GLM-5.2: 55.4 (#35)

| Benchmark | Command A | GLM-5.2 |
|---|---|---|
| LMArena Math | 1300 | 1482 |
| FrontierMath (Tiers 1-3) | — | 59.2% |
| FrontierMath Tier 4 | — | 29.3% |
| MathArena Final-Answer Competitions | — | 67.6% |
| OTIS Mock AIME 2024-2025 | — | 86.4% |
| ProofBench | — | 35% |

## Knowledge

- Command A: 36.5 (#157)
- GLM-5.2: 57.1 (#36)

| Benchmark | Command A | GLM-5.2 |
|---|---|---|
| LMArena Expert | 1295 | 1484 |
| GPQA Diamond | — | 91.9% |
| SimpleQA Verified | — | 34.2% |
| Vectara Hallucination Rate | 9.3% | — |

## Multilingual

- Command A: 45.5 (#166)
- GLM-5.2: 56.0 (#25)

| Benchmark | Command A | GLM-5.2 |
|---|---|---|
| LMArena Non-English | 1313 | 1459 |
| LMArena Chinese | 1327 | 1518 |
| LMArena French | 1352 | 1476 |
| LMArena German | 1341 | 1470 |
| LMArena Japanese | 1283 | 1451 |
| LMArena Korean | 1285 | 1445 |
| LMArena Russian | 1314 | 1467 |
| LMArena Spanish | 1346 | 1477 |

## Instruction Following

- Command A: 69.3 (#172)
- GLM-5.2: 77.1 (#32)

| Benchmark | Command A | GLM-5.2 |
|---|---|---|
| LMArena Instruction Following | 1309 | 1465 |

## Long Context

- Command A: 40.6 (#147)
- GLM-5.2: 45.3 (#43)

| Benchmark | Command A | GLM-5.2 |
|---|---|---|
| LMArena Longer Query | 1334 | 1479 |

## Writing & Preference

- Command A: 47.8 (#204)
- GLM-5.2: 70.7 (#20)

| Benchmark | Command A | GLM-5.2 |
|---|---|---|
| LMArena Text | 1331 | 1470 |
| LMArena Creative Writing | 1319 | 1465 |
| EQ-Bench Creative Writing | 1145 | 1757 |
| LMArena Multi-Turn | 1338 | 1468 |
| EQ-Bench 4 | — | 1222 |

## FAQ

### Is Command A better than GLM-5.2?

GLM-5.2 is the stronger model overall, scoring 50.9 to 35.9 on the Noometry Index.

### Which is cheaper, Command A or GLM-5.2?

GLM-5.2 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Command A lists at $2.50 and $10.

### Is Command A or GLM-5.2 better for coding?

GLM-5.2 scores higher on coding benchmarks: 50.9 versus 26.8 in the Noometry coding category.

### Which has the bigger context window?

GLM-5.2 does, with 1M tokens against 256K.

### How many benchmarks do Command A and GLM-5.2 share?

21 benchmarks have published results for both models. Command A has 24 scored results on Noometry and GLM-5.2 has 50.