# GLM-4.6 vs Granite 4.2 30b

> GLM-4.6 and Granite 4.2 30b score almost the same on the Noometry Index (40.9 vs 41.4), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/glm-4-6-vs-granite-4-2-30b
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. GLM-4.6 scores higher in 5 categories and Granite 4.2 30b in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6 leads 61.3 to 54.3.

## Snapshot

| | GLM-4.6 | Granite 4.2 30b |
|---|---|---|
| Provider | Z.ai (Zhipu) | IBM |
| Noometry Index | 40.9 | 41.4 |
| Rank | 132 | 126 |
| Context | 205K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.20 | — |
| Weights | Open | Open |

## Coding

- GLM-4.6: 39.9 (#137)
- Granite 4.2 30b: 40.4 (#127)

| Benchmark | GLM-4.6 | Granite 4.2 30b |
|---|---|---|
| LMArena Coding | 1449 | 1394 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1339 | — |
| SciCode | 38.4% | — |
| ALE-Bench | 340.82 | — |

## Agentic & Tool Use

- GLM-4.6: 32.1 (#60)
- Granite 4.2 30b: —

| Benchmark | GLM-4.6 | Granite 4.2 30b |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |

## Reasoning

- GLM-4.6: 23.1 (#168)
- Granite 4.2 30b: 26.7 (#114)

| Benchmark | GLM-4.6 | Granite 4.2 30b |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1375 |
| Kagi LLM Benchmark | 47.4% | — |
| CritPt | 1.1% | — |

## Math

- GLM-4.6: 36.4 (#115)
- Granite 4.2 30b: —

| Benchmark | GLM-4.6 | Granite 4.2 30b |
|---|---|---|
| LMArena Math | 1431 | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-4.6: 39.6 (#118)
- Granite 4.2 30b: 38.5 (#134)

| Benchmark | GLM-4.6 | Granite 4.2 30b |
|---|---|---|
| LMArena Expert | 1432 | 1405 |
| Vectara Hallucination Rate | 9.5% | — |

## Multilingual

- GLM-4.6: 53.6 (#62)
- Granite 4.2 30b: 47.4 (#146)

| Benchmark | GLM-4.6 | Granite 4.2 30b |
|---|---|---|
| LMArena Non-English | 1426 | 1340 |
| LMArena Chinese | 1500 | 1415 |
| LMArena Russian | 1418 | 1342 |
| LMArena French | 1459 | — |
| LMArena German | 1447 | — |
| LMArena Japanese | 1394 | — |
| LMArena Korean | 1401 | — |
| LMArena Spanish | 1436 | — |

## Instruction Following

- GLM-4.6: 74.5 (#93)
- Granite 4.2 30b: 71.3 (#150)

| Benchmark | GLM-4.6 | Granite 4.2 30b |
|---|---|---|
| LMArena Instruction Following | 1410 | 1346 |

## Long Context

- GLM-4.6: 43.4 (#91)
- Granite 4.2 30b: 41.4 (#135)

| Benchmark | GLM-4.6 | Granite 4.2 30b |
|---|---|---|
| LMArena Longer Query | 1423 | 1359 |

## Writing & Preference

- GLM-4.6: 61.3 (#86)
- Granite 4.2 30b: 54.3 (#147)

| Benchmark | GLM-4.6 | Granite 4.2 30b |
|---|---|---|
| LMArena Text | 1440 | 1363 |
| LMArena Creative Writing | 1411 | 1294 |
| LMArena Multi-Turn | 1427 | 1340 |
| EQ-Bench Creative Writing | 1411 | — |

## FAQ

### Is GLM-4.6 better than Granite 4.2 30b?

GLM-4.6 and Granite 4.2 30b score almost the same on the Noometry Index (40.9 vs 41.4), so choose on price, context window or the category you care about most.

### Is GLM-4.6 or Granite 4.2 30b better for coding?

They score almost the same on coding (39.9 vs 40.4); test both on your own repository before choosing.

### How many benchmarks do GLM-4.6 and Granite 4.2 30b share?

11 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Granite 4.2 30b has 11.