# Gemma 3 4B vs Qwen Plus

> Qwen Plus is the stronger model overall, scoring 37.1 to 28.1 on the Noometry Index. Gemma 3 4B costs 12× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-3-4b-vs-qwen-plus
- Last updated: 2026-10-11
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Qwen Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen Plus leads 27.4 to 11.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 25.2% for Gemma 3 4B and 63.3% for Qwen Plus.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.40 / $1.20 for Qwen Plus.
- Qwen Plus accepts more context: 1M tokens versus 131K.
- Gemma 3 4B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 3 4B | Qwen Plus |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 28.1 | 37.1 |
| Rank | 326 | 210 |
| Context | 131K | 1M |
| Input $/M | $0.04 | $0.40 |
| Output $/M | $0.08 | $1.20 |
| Weights | Open | Proprietary |

## Coding

- Gemma 3 4B: 35.9 (#215)
- Qwen Plus: 38.9 (#167)

| Benchmark | Gemma 3 4B | Qwen Plus |
|---|---|---|
| LMArena Coding | 1230 | 1328 |

## Agentic & Tool Use

- Gemma 3 4B: 20.9 (#142)
- Qwen Plus: —

| Benchmark | Gemma 3 4B | Qwen Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |

## Reasoning

- Gemma 3 4B: 13.2 (#335)
- Qwen Plus: 28.4 (#107)

| Benchmark | Gemma 3 4B | Qwen Plus |
|---|---|---|
| Kagi LLM Benchmark | 25.2% | 63.3% |
| LMArena Hard Prompts | 1253 | 1317 |
| DTBench | 50.9% | 81.1% |
| LMCA | 2.8% | 24% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 116.02 | — |

## Math

- Gemma 3 4B: 16.8 (#292)
- Qwen Plus: 23.3 (#271)

| Benchmark | Gemma 3 4B | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | 17.8% |
| LMArena Math | 1239 | 1326 |
| MATH Level 5 | — | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |

## Knowledge

- Gemma 3 4B: 11.8 (#299)
- Qwen Plus: 27.4 (#251)

| Benchmark | Gemma 3 4B | Qwen Plus |
|---|---|---|
| GPQA Diamond | 23.2% | 48.1% |
| LMArena Expert | 1223 | 1328 |
| Vectara Hallucination Rate | 6.4% | — |

## Multilingual

- Gemma 3 4B: 42.5 (#194)
- Qwen Plus: 45.1 (#175)

| Benchmark | Gemma 3 4B | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1273 | 1310 |
| LMArena Russian | 1294 | 1323 |
| LMArena Chinese | — | 1347 |
| LMArena German | 1281 | — |
| LMArena Japanese | — | 1251 |

## Instruction Following

- Gemma 3 4B: 65.2 (#225)
- Qwen Plus: 68.8 (#181)

| Benchmark | Gemma 3 4B | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1239 | 1303 |

## Long Context

- Gemma 3 4B: 38.7 (#194)
- Qwen Plus: 40.3 (#158)

| Benchmark | Gemma 3 4B | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1273 | 1324 |

## Writing & Preference

- Gemma 3 4B: 42.0 (#239)
- Qwen Plus: 52.2 (#176)

| Benchmark | Gemma 3 4B | Qwen Plus |
|---|---|---|
| LMArena Text | 1291 | 1326 |
| LMArena Creative Writing | 1271 | 1293 |
| LMArena Multi-Turn | 1255 | 1336 |
| EQ-Bench Creative Writing | 1068 | — |

## FAQ

### Is Gemma 3 4B better than Qwen Plus?

Qwen Plus is the stronger model overall, scoring 37.1 to 28.1 on the Noometry Index. Gemma 3 4B costs 12× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.

### Which is cheaper, Gemma 3 4B or Qwen Plus?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Qwen Plus lists at $0.40 and $1.20.

### Is Gemma 3 4B or Qwen Plus better for coding?

Qwen Plus scores higher on coding benchmarks: 38.9 versus 35.9 in the Noometry coding category.

### Which has the bigger context window?

Qwen Plus does, with 1M tokens against 131K.

### How many benchmarks do Gemma 3 4B and Qwen Plus share?

16 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Qwen Plus has 20.
