# Gemma 3 4B vs Mistral Small

> Mistral Small is the stronger model overall, scoring 33.1 to 27.9 on the Noometry Index. Gemma 3 4B costs 5.2× less per token, which makes it the better buy when Mistral Small's lead doesn't matter for your workload.

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

## Summary

- They share 19 benchmarks with published results for both. Gemma 3 4B scores higher in 2 categories and Mistral Small in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small leads 30.9 to 11.8.
- The biggest single-benchmark swing is GPQA Diamond: 23.2% for Gemma 3 4B and 47.5% for Mistral Small.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
- Mistral Small accepts more context: 256K tokens versus 131K.

## Snapshot

| | Gemma 3 4B | Mistral Small |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 27.9 | 33.1 |
| Rank | 320 | 238 |
| Context | 131K | 256K |
| Input $/M | $0.04 | $0.15 |
| Output $/M | $0.08 | $0.60 |
| Weights | Open | Open |

## Coding

- Gemma 3 4B: 35.3 (#214)
- Mistral Small: 33.5 (#242)

| Benchmark | Gemma 3 4B | Mistral Small |
|---|---|---|
| LMArena Coding | 1230 | 1363 |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |

## Agentic & Tool Use

- Gemma 3 4B: 20.7 (#134)
- Mistral Small: 27.9 (#87)

| Benchmark | Gemma 3 4B | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | 37.1% |

## Reasoning

- Gemma 3 4B: 12.7 (#330)
- Mistral Small: 19.3 (#238)

| Benchmark | Gemma 3 4B | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 25.2% | 37.8% |
| LMArena Hard Prompts | 1253 | 1336 |
| DTBench | 50.9% | 70.9% |
| LMCA | 2.8% | 20.6% |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| Epoch Capabilities Index | 116.02 | — |
| LiveBench | — | 44% |

## Math

- Gemma 3 4B: 15.8 (#286)
- Mistral Small: 15.4 (#287)

| Benchmark | Gemma 3 4B | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | 5.8% |
| LMArena Math | 1239 | 1341 |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |

## Knowledge

- Gemma 3 4B: 11.8 (#294)
- Mistral Small: 30.9 (#214)

| Benchmark | Gemma 3 4B | Mistral Small |
|---|---|---|
| GPQA Diamond | 23.2% | 47.5% |
| Vectara Hallucination Rate | 6.4% | 5.1% |
| LMArena Expert | 1223 | 1293 |
| MMLU | — | 68.7% |

## Multimodal

- Gemma 3 4B: —
- Mistral Small: 32.9 (#91)

| Benchmark | Gemma 3 4B | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |

## Multilingual

- Gemma 3 4B: 42.7 (#189)
- Mistral Small: 45.7 (#164)

| Benchmark | Gemma 3 4B | Mistral Small |
|---|---|---|
| LMArena Non-English | 1273 | 1315 |
| LMArena German | 1281 | 1341 |
| LMArena Russian | 1294 | 1324 |
| LMArena Chinese | — | 1342 |
| LMArena French | — | 1337 |
| LMArena Japanese | — | 1275 |
| LMArena Korean | — | 1260 |
| LMArena Spanish | — | 1346 |

## Instruction Following

- Gemma 3 4B: 65.4 (#219)
- Mistral Small: 66.6 (#204)

| Benchmark | Gemma 3 4B | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1239 | 1310 |
| LiveBench Instruction Following | — | 63.7% |

## Long Context

- Gemma 3 4B: 38.6 (#189)
- Mistral Small: 40.4 (#151)

| Benchmark | Gemma 3 4B | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1274 | 1327 |

## Writing & Preference

- Gemma 3 4B: 42.2 (#234)
- Mistral Small: 52.6 (#165)

| Benchmark | Gemma 3 4B | Mistral Small |
|---|---|---|
| LMArena Text | 1291 | 1338 |
| LMArena Creative Writing | 1270 | 1304 |
| LMArena Multi-Turn | 1255 | 1344 |
| EQ-Bench Creative Writing | 1068 | — |
| LiveBench Language | — | 30.5% |

## FAQ

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

Mistral Small is the stronger model overall, scoring 33.1 to 27.9 on the Noometry Index. Gemma 3 4B costs 5.2× less per token, which makes it the better buy when Mistral Small's lead doesn't matter for your workload.

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

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Mistral Small lists at $0.15 and $0.60.

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

Gemma 3 4B scores higher on coding benchmarks: 35.3 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

Mistral Small does, with 256K tokens against 131K.

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

19 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Mistral Small has 39.