# GLM-4.6V vs Step 5 Preview

> Step 5 Preview is the stronger model overall, scoring 47.9 to 41.3 on the Noometry Index. GLM-4.6V costs 3.2× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-4-6v-vs-step-5-preview
- Last updated: 2026-10-12
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. GLM-4.6V scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 27.6.
- GLM-4.6V is cheaper at $0.30 / $0.90 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 128K.
- GLM-4.6V has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-4.6V | Step 5 Preview |
|---|---|---|
| Provider | Z.ai (Zhipu) | StepFun |
| Noometry Index | 41.3 | 47.9 |
| Rank | 137 | 58 |
| Context | 128K | 1.02M |
| Input $/M | $0.30 | $1 |
| Output $/M | $0.90 | $2.70 |
| Weights | Open | Proprietary |

## Coding

- GLM-4.6V: 40.9 (#128)
- Step 5 Preview: 51.8 (#36)

| Benchmark | GLM-4.6V | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1390 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |

## Reasoning

- GLM-4.6V: 27.6 (#115)
- Step 5 Preview: 40.0 (#57)

| Benchmark | GLM-4.6V | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1368 | 1465 |
| CritPt | — | 20.9% |

## Math

- GLM-4.6V: —
- Step 5 Preview: 46.1 (#72)

| Benchmark | GLM-4.6V | Step 5 Preview |
|---|---|---|
| ProofBench | — | 42% |
| LMArena Math | — | 1470 |

## Knowledge

- GLM-4.6V: 38.0 (#149)
- Step 5 Preview: 41.2 (#112)

| Benchmark | GLM-4.6V | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1371 | 1470 |

## Multimodal

- GLM-4.6V: 34.8 (#90)
- Step 5 Preview: 41.0 (#41)

| Benchmark | GLM-4.6V | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1164 | 1267 |

## Multilingual

- GLM-4.6V: 48.6 (#141)
- Step 5 Preview: 53.8 (#54)

| Benchmark | GLM-4.6V | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1359 | 1432 |
| LMArena Chinese | 1425 | 1519 |
| LMArena Russian | 1340 | 1436 |
| LMArena Spanish | — | 1439 |

## Instruction Following

- GLM-4.6V: 71.4 (#151)
- Step 5 Preview: 76.0 (#50)

| Benchmark | GLM-4.6V | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1352 | 1444 |

## Long Context

- GLM-4.6V: 41.3 (#143)
- Step 5 Preview: 44.5 (#64)

| Benchmark | GLM-4.6V | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1358 | 1455 |

## Writing & Preference

- GLM-4.6V: 56.6 (#137)
- Step 5 Preview: 62.8 (#71)

| Benchmark | GLM-4.6V | Step 5 Preview |
|---|---|---|
| LMArena Text | 1377 | 1442 |
| LMArena Creative Writing | 1347 | 1410 |
| LMArena Multi-Turn | 1360 | 1447 |

## FAQ

### Is GLM-4.6V better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 41.3 on the Noometry Index. GLM-4.6V costs 3.2× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

### Which is cheaper, GLM-4.6V or Step 5 Preview?

GLM-4.6V is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Step 5 Preview lists at $1 and $2.70.

### Is GLM-4.6V or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 40.9 in the Noometry coding category.

### Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 128K.

### How many benchmarks do GLM-4.6V and Step 5 Preview share?

12 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and Step 5 Preview has 18.