# Gemma 2 9B vs GLM-5.3

> GLM-5.3 is the stronger model overall, scoring 54.8 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-9b-vs-glm-5-3
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and GLM-5.3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.3 leads 62.3 to 9.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 91.1% for GLM-5.3.

## Snapshot

| | Gemma 2 9B | GLM-5.3 |
|---|---|---|
| Provider | Google | Z.ai (Zhipu) |
| Noometry Index | 25.9 | 54.8 |
| Rank | 341 | 26 |
| Context | — | 1M |
| Input $/M | — | $1.40 |
| Output $/M | — | $4.40 |
| Weights | Open | Open |

## Coding

- Gemma 2 9B: 29.4 (#304)
- GLM-5.3: 59.5 (#14)

| Benchmark | Gemma 2 9B | GLM-5.3 |
|---|---|---|
| LMArena Coding | 1173 | 1496 |
| DeepSWE | — | 69% |
| FrontierCode | — | 40.1% |
| CursorBench | — | 42.6% |
| LMArena WebDev | — | 1622 |
| FrontierSWE | — | 30.2% |
| SciCode | — | 59% |
| WeirdML | — | 75.4% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
| ALE-Bench | — | 1,317 |

## Agentic & Tool Use

- Gemma 2 9B: —
- GLM-5.3: 36.4 (#38)

| Benchmark | Gemma 2 9B | GLM-5.3 |
|---|---|---|
| APEX-Agents | — | 56.6% |
| Vending-Bench 2 | — | 8,164 |

## Reasoning

- Gemma 2 9B: 15.9 (#309)
- GLM-5.3: 46.1 (#46)

| Benchmark | Gemma 2 9B | GLM-5.3 |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1489 |
| Epoch Capabilities Index | 119.83 | 155.61 |
| NYT Connections (extended) | — | 74.2% |
| CritPt | — | 19.1% |
| Chess Puzzles | — | 21% |
| LiveBench Reasoning | 15.2% | — |
| Mystery Game Puzzles | — | 33% |
| DTBench | — | 87.7% |
| LiveBench Data Analysis | 36.4% | — |
| LMCA | — | 55.5% |
| Bench to the Future 3 | — | 0.15 |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |

## Math

- Gemma 2 9B: 9.9 (#318)
- GLM-5.3: 62.3 (#33)

| Benchmark | Gemma 2 9B | GLM-5.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 91.1% |
| LMArena Math | 1183 | 1489 |
| FrontierMath (Tiers 1-3) | — | 68.8% |
| FrontierMath Tier 4 | — | 29.3% |
| ProofBench | — | 49% |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |

## Knowledge

- Gemma 2 9B: 9.7 (#305)
- GLM-5.3: 58.3 (#37)

| Benchmark | Gemma 2 9B | GLM-5.3 |
|---|---|---|
| GPQA Diamond | 27.5% | 90.9% |
| LMArena Expert | 1147 | 1516 |
| SimpleQA Verified | — | 41% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |

## Multilingual

- Gemma 2 9B: 36.6 (#238)
- GLM-5.3: 55.7 (#28)

| Benchmark | Gemma 2 9B | GLM-5.3 |
|---|---|---|
| LMArena Non-English | 1188 | 1457 |
| LMArena Chinese | 1185 | 1528 |
| LMArena French | 1190 | 1499 |
| LMArena German | 1186 | 1499 |
| LMArena Japanese | 1144 | 1453 |
| LMArena Korean | 1137 | 1472 |
| LMArena Russian | 1200 | 1463 |
| LMArena Spanish | 1200 | 1460 |

## Instruction Following

- Gemma 2 9B: 57.6 (#269)
- GLM-5.3: 77.5 (#23)

| Benchmark | Gemma 2 9B | GLM-5.3 |
|---|---|---|
| LMArena Instruction Following | 1178 | 1477 |
| LiveBench Instruction Following | 52.6% | — |

## Long Context

- Gemma 2 9B: 36.3 (#233)
- GLM-5.3: 45.4 (#41)

| Benchmark | Gemma 2 9B | GLM-5.3 |
|---|---|---|
| LMArena Longer Query | 1197 | 1482 |

## Writing & Preference

- Gemma 2 9B: 32.1 (#281)
- GLM-5.3: 75.7 (#6)

| Benchmark | Gemma 2 9B | GLM-5.3 |
|---|---|---|
| LMArena Text | 1207 | 1471 |
| LMArena Creative Writing | 1206 | 1457 |
| EQ-Bench Creative Writing | 841 | 2075 |
| LMArena Multi-Turn | 1193 | 1472 |
| LiveBench Language | 25.5% | — |

## FAQ

### Is Gemma 2 9B better than GLM-5.3?

GLM-5.3 is the stronger model overall, scoring 54.8 to 25.9 on the Noometry Index.

### Is Gemma 2 9B or GLM-5.3 better for coding?

GLM-5.3 scores higher on coding benchmarks: 59.5 versus 29.4 in the Noometry coding category.

### How many benchmarks do Gemma 2 9B and GLM-5.3 share?

21 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and GLM-5.3 has 42.