# Gemma 3 4B vs GLM-5

> GLM-5 is the stronger model overall, scoring 46.1 to 28.1 on the Noometry Index. Gemma 3 4B costs 31× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-3-4b-vs-glm-5
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and GLM-5 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.3 to 11.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.5% for Gemma 3 4B and 80% for GLM-5.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $1 / $3.20 for GLM-5.
- GLM-5 accepts more context: 205K tokens versus 131K.

## Snapshot

| | Gemma 3 4B | GLM-5 |
|---|---|---|
| Provider | Google | Z.ai (Zhipu) |
| Noometry Index | 28.1 | 46.1 |
| Rank | 326 | 66 |
| Context | 131K | 205K |
| Input $/M | $0.04 | $1 |
| Output $/M | $0.08 | $3.20 |
| Weights | Open | Open |

## Coding

- Gemma 3 4B: 35.9 (#215)
- GLM-5: 49.0 (#52)

| Benchmark | Gemma 3 4B | GLM-5 |
|---|---|---|
| LMArena Coding | 1230 | 1461 |
| SWE-bench Verified | — | 72.1% |
| SWE-bench Verified (bash only) | — | 72.8% |
| LMArena WebDev | — | 1434 |
| SWE-bench Multilingual | — | 69.7% |
| WeirdML | — | 48.2% |
| ALE-Bench | — | 765.62 |

## Agentic & Tool Use

- Gemma 3 4B: 20.9 (#142)
- GLM-5: 31.1 (#71)

| Benchmark | Gemma 3 4B | GLM-5 |
|---|---|---|
| Terminal-Bench | — | 52.4% |
| Berkeley Function Calling Leaderboard | 19.6% | — |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 73.7% |
| τ²-bench Telecom | — | 86.8% |
| Vending-Bench 2 | — | 4,432 |

## Reasoning

- Gemma 3 4B: 13.2 (#335)
- GLM-5: 27.6 (#116)

| Benchmark | Gemma 3 4B | GLM-5 |
|---|---|---|
| Kagi LLM Benchmark | 25.2% | 75% |
| Chess Puzzles | 0% | 10% |
| LMArena Hard Prompts | 1253 | 1452 |
| Epoch Capabilities Index | 116.02 | 145.83 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | — | 53.2% |
| NYT Connections (extended) | — | 74.8% |
| ARC-AGI-1 | — | 44.7% |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| ForecastBench | — | 61 |

## Math

- Gemma 3 4B: 16.8 (#292)
- GLM-5: 46.4 (#71)

| Benchmark | Gemma 3 4B | GLM-5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | 80% |
| LMArena Math | 1239 | 1440 |
| MathArena Final-Answer Competitions | — | 65.7% |
| FrontierMath (Feb 2025 set) | — | 16.4% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Gemma 3 4B: 11.8 (#299)
- GLM-5: 52.3 (#64)

| Benchmark | Gemma 3 4B | GLM-5 |
|---|---|---|
| GPQA Diamond | 23.2% | 87.8% |
| Vectara Hallucination Rate | 6.4% | 10.1% |
| LMArena Expert | 1223 | 1454 |

## Multilingual

- Gemma 3 4B: 42.5 (#194)
- GLM-5: 53.7 (#58)

| Benchmark | Gemma 3 4B | GLM-5 |
|---|---|---|
| LMArena Non-English | 1273 | 1430 |
| LMArena German | 1281 | 1445 |
| LMArena Russian | 1294 | 1436 |
| LMArena Chinese | — | 1511 |
| LMArena French | — | 1455 |
| LMArena Japanese | — | 1416 |
| LMArena Korean | — | 1423 |
| LMArena Spanish | — | 1454 |

## Instruction Following

- Gemma 3 4B: 65.2 (#225)
- GLM-5: 75.2 (#67)

| Benchmark | Gemma 3 4B | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1239 | 1428 |

## Long Context

- Gemma 3 4B: 38.7 (#194)
- GLM-5: 44.7 (#60)

| Benchmark | Gemma 3 4B | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1273 | 1446 |
| CL-bench | — | 18.7% |

## Writing & Preference

- Gemma 3 4B: 42.0 (#239)
- GLM-5: 66.0 (#38)

| Benchmark | Gemma 3 4B | GLM-5 |
|---|---|---|
| LMArena Text | 1291 | 1446 |
| LMArena Creative Writing | 1271 | 1439 |
| EQ-Bench Creative Writing | 1068 | 1601 |
| LMArena Multi-Turn | 1255 | 1456 |

## FAQ

### Is Gemma 3 4B better than GLM-5?

GLM-5 is the stronger model overall, scoring 46.1 to 28.1 on the Noometry Index. Gemma 3 4B costs 31× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.

### Which is cheaper, Gemma 3 4B or GLM-5?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; GLM-5 lists at $1 and $3.20.

### Is Gemma 3 4B or GLM-5 better for coding?

GLM-5 scores higher on coding benchmarks: 49.0 versus 35.9 in the Noometry coding category.

### Which has the bigger context window?

GLM-5 does, with 205K tokens against 131K.

### How many benchmarks do Gemma 3 4B and GLM-5 share?

19 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and GLM-5 has 45.