# GLM-4.7 vs Step 5 Preview

> Step 5 Preview is the stronger model overall, scoring 47.9 to 42.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-7-vs-step-5-preview
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GLM-4.7 scores higher in 1 category and Step 5 Preview in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 24.3.
- The biggest single-benchmark swing is ProofBench: 6% for GLM-4.7 and 42% for Step 5 Preview.
- GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 205K.
- GLM-4.7 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-4.7 | Step 5 Preview |
|---|---|---|
| Provider | Z.ai (Zhipu) | StepFun |
| Noometry Index | 42.0 | 47.9 |
| Rank | 124 | 58 |
| Context | 205K | 1.02M |
| Input $/M | $0.60 | $1 |
| Output $/M | $2.20 | $2.70 |
| Weights | Open | Proprietary |

## Coding

- GLM-4.7: 44.0 (#79)
- Step 5 Preview: 51.8 (#36)

| Benchmark | GLM-4.7 | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1435 | 1564 |
| SciCode | 45.1% | 58.9% |
| LMArena Coding | 1454 | 1480 |
| ALE-Bench | 399.48 | — |

## Agentic & Tool Use

- GLM-4.7: 26.5 (#103)
- Step 5 Preview: —

| Benchmark | GLM-4.7 | Step 5 Preview |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Vending-Bench 2 | 2,377 | — |

## Reasoning

- GLM-4.7: 24.3 (#164)
- Step 5 Preview: 40.0 (#57)

| Benchmark | GLM-4.7 | Step 5 Preview |
|---|---|---|
| CritPt | 1.7% | 20.9% |
| LMArena Hard Prompts | 1443 | 1465 |
| SimpleBench | 47.7% | — |
| Chess Puzzles | 6% | — |
| Epoch Capabilities Index | 143.51 | — |

## Math

- GLM-4.7: 38.6 (#135)
- Step 5 Preview: 46.1 (#72)

| Benchmark | GLM-4.7 | Step 5 Preview |
|---|---|---|
| ProofBench | 6% | 42% |
| LMArena Math | 1423 | 1470 |
| OTIS Mock AIME 2024-2025 | 83.3% | — |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- GLM-4.7: 47.0 (#80)
- Step 5 Preview: 41.2 (#112)

| Benchmark | GLM-4.7 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1424 | 1470 |
| GPQA Diamond | 83.3% | — |
| SimpleQA Verified | 32.2% | — |
| Vectara Hallucination Rate | 11.7% | — |

## Multimodal

- GLM-4.7: —
- Step 5 Preview: 41.0 (#41)

| Benchmark | GLM-4.7 | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |

## Multilingual

- GLM-4.7: 52.8 (#79)
- Step 5 Preview: 53.8 (#54)

| Benchmark | GLM-4.7 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1417 | 1432 |
| LMArena Chinese | 1495 | 1519 |
| LMArena Russian | 1423 | 1436 |
| LMArena Spanish | 1434 | 1439 |
| LMArena French | 1432 | — |
| LMArena German | 1424 | — |
| LMArena Japanese | 1439 | — |
| LMArena Korean | 1399 | — |

## Instruction Following

- GLM-4.7: 74.4 (#95)
- Step 5 Preview: 76.0 (#50)

| Benchmark | GLM-4.7 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1411 | 1444 |

## Long Context

- GLM-4.7: 42.8 (#116)
- Step 5 Preview: 44.5 (#64)

| Benchmark | GLM-4.7 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1432 | 1455 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |

## Writing & Preference

- GLM-4.7: 60.9 (#93)
- Step 5 Preview: 62.8 (#71)

| Benchmark | GLM-4.7 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1435 | 1442 |
| LMArena Creative Writing | 1401 | 1410 |
| LMArena Multi-Turn | 1446 | 1447 |
| EQ-Bench Creative Writing | 1413 | — |

## FAQ

### Is GLM-4.7 better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 42.0 on the Noometry Index.

### Which is cheaper, GLM-4.7 or Step 5 Preview?

GLM-4.7 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Step 5 Preview lists at $1 and $2.70.

### Is GLM-4.7 or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 44.0 in the Noometry coding category.

### Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 205K.

### How many benchmarks do GLM-4.7 and Step 5 Preview share?

17 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Step 5 Preview has 18.