# Gemma 7B vs GLM-4.6

> GLM-4.6 is the stronger model overall, scoring 40.9 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-7b-vs-glm-4-6
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Gemma 7B scores higher in 0 categories and GLM-4.6 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6 leads 61.3 to 27.2.

## Snapshot

| | Gemma 7B | GLM-4.6 |
|---|---|---|
| Provider | Google | Z.ai (Zhipu) |
| Noometry Index | 29.5 | 40.9 |
| Rank | 295 | 132 |
| Context | — | 205K |
| Input $/M | — | $0.60 |
| Output $/M | — | $2.20 |
| Weights | Open | Open |

## Coding

- Gemma 7B: 29.9 (#290)
- GLM-4.6: 39.9 (#137)

| Benchmark | Gemma 7B | GLM-4.6 |
|---|---|---|
| LMArena Coding | 1048 | 1449 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1339 |
| SciCode | — | 38.4% |
| ALE-Bench | — | 340.82 |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |

## Agentic & Tool Use

- Gemma 7B: —
- GLM-4.6: 32.1 (#60)

| Benchmark | Gemma 7B | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| Berkeley Function Calling Leaderboard | — | 72.4% |

## Reasoning

- Gemma 7B: 19.0 (#247)
- GLM-4.6: 23.1 (#168)

| Benchmark | Gemma 7B | GLM-4.6 |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1440 |
| Kagi LLM Benchmark | — | 47.4% |
| CritPt | — | 1.1% |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| Epoch Capabilities Index | 111.74 | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |

## Math

- Gemma 7B: 28.7 (#225)
- GLM-4.6: 36.4 (#115)

| Benchmark | Gemma 7B | GLM-4.6 |
|---|---|---|
| LMArena Math | 1066 | 1431 |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
| GSM8K | 46.4% | — |

## Knowledge

- Gemma 7B: 26.8 (#248)
- GLM-4.6: 39.6 (#118)

| Benchmark | Gemma 7B | GLM-4.6 |
|---|---|---|
| LMArena Expert | 1002 | 1432 |
| Vectara Hallucination Rate | — | 9.5% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |

## Multilingual

- Gemma 7B: 25.3 (#282)
- GLM-4.6: 53.6 (#62)

| Benchmark | Gemma 7B | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 999 | 1426 |
| LMArena Chinese | 1035 | 1500 |
| LMArena French | 1024 | 1459 |
| LMArena Russian | 993 | 1418 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1394 |
| LMArena Korean | — | 1401 |
| LMArena Spanish | — | 1436 |

## Instruction Following

- Gemma 7B: 51.7 (#290)
- GLM-4.6: 74.5 (#93)

| Benchmark | Gemma 7B | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1017 | 1410 |

## Long Context

- Gemma 7B: 31.1 (#277)
- GLM-4.6: 43.4 (#91)

| Benchmark | Gemma 7B | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1022 | 1423 |

## Writing & Preference

- Gemma 7B: 27.2 (#297)
- GLM-4.6: 61.3 (#86)

| Benchmark | Gemma 7B | GLM-4.6 |
|---|---|---|
| LMArena Text | 1056 | 1440 |
| LMArena Creative Writing | 1024 | 1411 |
| LMArena Multi-Turn | 963 | 1427 |
| EQ-Bench Creative Writing | — | 1411 |

## FAQ

### Is Gemma 7B better than GLM-4.6?

GLM-4.6 is the stronger model overall, scoring 40.9 to 29.5 on the Noometry Index.

### Is Gemma 7B or GLM-4.6 better for coding?

GLM-4.6 scores higher on coding benchmarks: 39.9 versus 29.9 in the Noometry coding category.

### How many benchmarks do Gemma 7B and GLM-4.6 share?

13 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and GLM-4.6 has 29.