# Gemma 3 4B vs Mistral Small 3

> Mistral Small 3 is the stronger model overall, scoring 31.2 to 28.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-4b-vs-mistral-small-3
- Last updated: 2026-10-11
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Gemma 3 4B scores higher in 5 categories and Mistral Small 3 in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small 3 leads 25.1 to 11.8.
- The biggest single-benchmark swing is GPQA Diamond: 23.2% for Gemma 3 4B and 47.3% for Mistral Small 3.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.05 / $0.08 for Mistral Small 3.
- Gemma 3 4B accepts more context: 131K tokens versus 33K.

## Snapshot

| | Gemma 3 4B | Mistral Small 3 |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 28.1 | 31.2 |
| Rank | 326 | 278 |
| Context | 131K | 33K |
| Input $/M | $0.04 | $0.05 |
| Output $/M | $0.08 | $0.08 |
| Weights | Open | Open |

## Coding

- Gemma 3 4B: 35.9 (#215)
- Mistral Small 3: 36.5 (#207)

| Benchmark | Gemma 3 4B | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1230 | 1246 |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |

## Agentic & Tool Use

- Gemma 3 4B: 20.9 (#142)
- Mistral Small 3: —

| Benchmark | Gemma 3 4B | Mistral Small 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |

## Reasoning

- Gemma 3 4B: 13.2 (#335)
- Mistral Small 3: 18.9 (#273)

| Benchmark | Gemma 3 4B | Mistral Small 3 |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1253 | 1233 |
| Epoch Capabilities Index | 116.02 | 127.07 |
| Kagi LLM Benchmark | 25.2% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |

## Math

- Gemma 3 4B: 16.8 (#292)
- Mistral Small 3: 16.3 (#295)

| Benchmark | Gemma 3 4B | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | 6.7% |
| LMArena Math | 1239 | 1240 |

## Knowledge

- Gemma 3 4B: 11.8 (#299)
- Mistral Small 3: 25.1 (#263)

| Benchmark | Gemma 3 4B | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 23.2% | 47.3% |
| LMArena Expert | 1223 | 1202 |
| Confabulations | — | 25.2% |
| Vectara Hallucination Rate | 6.4% | — |

## Multilingual

- Gemma 3 4B: 42.5 (#194)
- Mistral Small 3: 37.3 (#236)

| Benchmark | Gemma 3 4B | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1273 | 1198 |
| LMArena German | 1281 | 1211 |
| LMArena Russian | 1294 | 1216 |
| LMArena Chinese | — | 1204 |
| LMArena French | — | 1203 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1188 |

## Instruction Following

- Gemma 3 4B: 65.2 (#225)
- Mistral Small 3: 63.7 (#229)

| Benchmark | Gemma 3 4B | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1239 | 1214 |

## Long Context

- Gemma 3 4B: 38.7 (#194)
- Mistral Small 3: 37.8 (#211)

| Benchmark | Gemma 3 4B | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1273 | 1246 |

## Writing & Preference

- Gemma 3 4B: 42.0 (#239)
- Mistral Small 3: 32.2 (#280)

| Benchmark | Gemma 3 4B | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1291 | 1234 |
| LMArena Creative Writing | 1271 | 1195 |
| EQ-Bench Creative Writing | 1068 | 707 |
| LMArena Multi-Turn | 1255 | 1217 |

## FAQ

### Is Gemma 3 4B better than Mistral Small 3?

Mistral Small 3 is the stronger model overall, scoring 31.2 to 28.1 on the Noometry Index.

### Which is cheaper, Gemma 3 4B or Mistral Small 3?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Mistral Small 3 lists at $0.05 and $0.08.

### Is Gemma 3 4B or Mistral Small 3 better for coding?

They score almost the same on coding (35.9 vs 36.5); test both on your own repository before choosing.

### Which has the bigger context window?

Gemma 3 4B does, with 131K tokens against 33K.

### How many benchmarks do Gemma 3 4B and Mistral Small 3 share?

17 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Mistral Small 3 has 24.