# Devstral Small 2505 vs Gemma 3 4B

> Devstral Small 2505 is the stronger model overall, scoring 34.3 to 28.1 on the Noometry Index. Gemma 3 4B costs 3.0× less per token, which makes it the better buy when Devstral Small 2505's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/devstral-small-vs-gemma-3-4b
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Devstral Small 2505 scores higher in 2 categories and Gemma 3 4B in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Devstral Small 2505 leads 19.7 to 13.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.7% for Devstral Small 2505 and 25.2% for Gemma 3 4B.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.10 / $0.30 for Devstral Small 2505.
- Gemma 3 4B accepts more context: 131K tokens versus 128K.

## Snapshot

| | Devstral Small 2505 | Gemma 3 4B |
|---|---|---|
| Provider | Mistral AI | Google |
| Noometry Index | 34.3 | 28.1 |
| Rank | 233 | 326 |
| Context | 128K | 131K |
| Input $/M | $0.10 | $0.04 |
| Output $/M | $0.30 | $0.08 |
| Weights | Open | Open |

## Coding

- Devstral Small 2505: 38.9 (#166)
- Gemma 3 4B: 35.9 (#215)

| Benchmark | Devstral Small 2505 | Gemma 3 4B |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1230 |

## Agentic & Tool Use

- Devstral Small 2505: —
- Gemma 3 4B: 20.9 (#142)

| Benchmark | Devstral Small 2505 | Gemma 3 4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 19.6% |

## Reasoning

- Devstral Small 2505: 19.7 (#252)
- Gemma 3 4B: 13.2 (#335)

| Benchmark | Devstral Small 2505 | Gemma 3 4B |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | 25.2% |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1253 |
| DTBench | — | 50.9% |
| LMCA | — | 2.8% |
| Epoch Capabilities Index | — | 116.02 |

## Math

- Devstral Small 2505: —
- Gemma 3 4B: 16.8 (#292)

| Benchmark | Devstral Small 2505 | Gemma 3 4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 7.5% |
| LMArena Math | — | 1239 |

## Knowledge

- Devstral Small 2505: —
- Gemma 3 4B: 11.8 (#299)

| Benchmark | Devstral Small 2505 | Gemma 3 4B |
|---|---|---|
| GPQA Diamond | — | 23.2% |
| Vectara Hallucination Rate | — | 6.4% |
| LMArena Expert | — | 1223 |

## Multilingual

- Devstral Small 2505: —
- Gemma 3 4B: 42.5 (#194)

| Benchmark | Devstral Small 2505 | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | — | 1273 |
| LMArena German | — | 1281 |
| LMArena Russian | — | 1294 |

## Instruction Following

- Devstral Small 2505: —
- Gemma 3 4B: 65.2 (#225)

| Benchmark | Devstral Small 2505 | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | — | 1239 |

## Long Context

- Devstral Small 2505: —
- Gemma 3 4B: 38.7 (#194)

| Benchmark | Devstral Small 2505 | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | — | 1273 |

## Writing & Preference

- Devstral Small 2505: —
- Gemma 3 4B: 42.0 (#239)

| Benchmark | Devstral Small 2505 | Gemma 3 4B |
|---|---|---|
| LMArena Text | — | 1291 |
| LMArena Creative Writing | — | 1271 |
| EQ-Bench Creative Writing | — | 1068 |
| LMArena Multi-Turn | — | 1255 |

## FAQ

### Is Devstral Small 2505 better than Gemma 3 4B?

Devstral Small 2505 is the stronger model overall, scoring 34.3 to 28.1 on the Noometry Index. Gemma 3 4B costs 3.0× less per token, which makes it the better buy when Devstral Small 2505's lead doesn't matter for your workload.

### Which is cheaper, Devstral Small 2505 or Gemma 3 4B?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Devstral Small 2505 lists at $0.10 and $0.30.

### Is Devstral Small 2505 or Gemma 3 4B better for coding?

Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 35.9 in the Noometry coding category.

### Which has the bigger context window?

Gemma 3 4B does, with 131K tokens against 128K.

### How many benchmarks do Devstral Small 2505 and Gemma 3 4B share?

1 benchmark has published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Gemma 3 4B has 22.