# Gemma 4 31B IT vs Magistral Small

> Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 29.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-4-31b-it-vs-magistral-small
- Last updated: 2026-10-10
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. Gemma 4 31B IT scores higher in 4 categories and Magistral Small in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemma 4 31B IT leads 26.4 to 6.9.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 63.5% for Gemma 4 31B IT and 6.3% for Magistral Small.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.50 / $1.50 for Magistral Small.
- Gemma 4 31B IT accepts more context: 262K tokens versus 128K.

## Snapshot

| | Gemma 4 31B IT | Magistral Small |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 43.2 | 29.9 |
| Rank | 85 | 289 |
| Context | 262K | 128K |
| Input $/M | $0.09 | $0.50 |
| Output $/M | $0.34 | $1.50 |
| Weights | Open | Open |

## Coding

- Gemma 4 31B IT: 41.9 (#98)
- Magistral Small: 37.8 (#172)

| Benchmark | Gemma 4 31B IT | Magistral Small |
|---|---|---|
| SciCode | 43.4% | 35.2% |
| LMArena WebDev | 1364 | — |
| WeirdML | 52.3% | — |
| LMArena Coding | 1459 | — |
| ALE-Bench | 925.5 | — |

## Reasoning

- Gemma 4 31B IT: 26.4 (#119)
- Magistral Small: 6.9 (#345)

| Benchmark | Gemma 4 31B IT | Magistral Small |
|---|---|---|
| Kagi LLM Benchmark | 63.5% | 6.3% |
| CritPt | 1.4% | 0.3% |
| Chess Puzzles | 5% | 3% |
| DTBench | 82.7% | 61.3% |
| Epoch Capabilities Index | 142.74 | 133.19 |
| ARC-AGI-2 | — | 0% |
| NYT Connections (extended) | 70.6% | — |
| ARC-AGI-1 | — | 5% |
| Thematic Generalization | 53% | — |
| LMArena Hard Prompts | 1448 | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |

## Math

- Gemma 4 31B IT: 41.3 (#72)
- Magistral Small: 24.9 (#253)

| Benchmark | Gemma 4 31B IT | Magistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 30% |
| LMArena Math | 1464 | — |

## Knowledge

- Gemma 4 31B IT: 37.9 (#141)
- Magistral Small: 30.9 (#215)

| Benchmark | Gemma 4 31B IT | Magistral Small |
|---|---|---|
| GPQA Diamond | 75.8% | 56.1% |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
| LMArena Expert | 1465 | — |

## Multimodal

- Gemma 4 31B IT: 41.0 (#32)
- Magistral Small: —

| Benchmark | Gemma 4 31B IT | Magistral Small |
|---|---|---|
| LMArena Vision | 1278 | — |
| LMArena Document | 1425 | — |

## Multilingual

- Gemma 4 31B IT: 54.0 (#52)
- Magistral Small: —

| Benchmark | Gemma 4 31B IT | Magistral Small |
|---|---|---|
| LMArena Non-English | 1431 | — |
| LMArena Chinese | 1478 | — |
| LMArena French | 1436 | — |
| LMArena Russian | 1462 | — |
| LMArena Spanish | 1443 | — |

## Instruction Following

- Gemma 4 31B IT: 75.6 (#58)
- Magistral Small: —

| Benchmark | Gemma 4 31B IT | Magistral Small |
|---|---|---|
| LMArena Instruction Following | 1433 | — |

## Long Context

- Gemma 4 31B IT: 44.2 (#67)
- Magistral Small: —

| Benchmark | Gemma 4 31B IT | Magistral Small |
|---|---|---|
| LMArena Longer Query | 1446 | — |

## Writing & Preference

- Gemma 4 31B IT: 60.7 (#92)
- Magistral Small: —

| Benchmark | Gemma 4 31B IT | Magistral Small |
|---|---|---|
| LMArena Text | 1443 | — |
| LMArena Creative Writing | 1416 | — |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
| LMArena Multi-Turn | 1452 | — |

## FAQ

### Is Gemma 4 31B IT better than Magistral Small?

Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 29.9 on the Noometry Index.

### Which is cheaper, Gemma 4 31B IT or Magistral Small?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Magistral Small lists at $0.50 and $1.50.

### Is Gemma 4 31B IT or Magistral Small better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 37.8 in the Noometry coding category.

### Which has the bigger context window?

Gemma 4 31B IT does, with 262K tokens against 128K.

### How many benchmarks do Gemma 4 31B IT and Magistral Small share?

8 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Magistral Small has 10.