# Gemma 4 31B IT vs MiniMax-M3

> Gemma 4 31B IT and MiniMax-M3 score almost the same on the Noometry Index (43.2 vs 43.5), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gemma-4-31b-it-vs-minimax-m3
- Last updated: 2026-10-10
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. Gemma 4 31B IT scores higher in 5 categories and MiniMax-M3 in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 37.9.
- The biggest single-benchmark swing is Surface Evolver Bench: 30.6% for Gemma 4 31B IT and 55% for MiniMax-M3.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
- MiniMax-M3 accepts more context: 1M tokens versus 262K.

## Snapshot

| | Gemma 4 31B IT | MiniMax-M3 |
|---|---|---|
| Provider | Google | MiniMax |
| Noometry Index | 43.2 | 43.5 |
| Rank | 85 | 81 |
| Context | 262K | 1M |
| Input $/M | $0.09 | $0.30 |
| Output $/M | $0.34 | $1.20 |
| Weights | Open | Open |

## Coding

- Gemma 4 31B IT: 41.9 (#98)
- MiniMax-M3: 41.5 (#111)

| Benchmark | Gemma 4 31B IT | MiniMax-M3 |
|---|---|---|
| LMArena WebDev | 1364 | 1482 |
| SciCode | 43.4% | 47.1% |
| LMArena Coding | 1459 | 1470 |
| ALE-Bench | 925.5 | 640.02 |
| FrontierCode | — | 14.7% |
| WeirdML | 52.3% | — |

## Agentic & Tool Use

- Gemma 4 31B IT: —
- MiniMax-M3: 22.5 (#121)

| Benchmark | Gemma 4 31B IT | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |

## Reasoning

- Gemma 4 31B IT: 26.4 (#119)
- MiniMax-M3: 29.3 (#83)

| Benchmark | Gemma 4 31B IT | MiniMax-M3 |
|---|---|---|
| NYT Connections (extended) | 70.6% | 65.1% |
| CritPt | 1.4% | 3.7% |
| Chess Puzzles | 5% | 14% |
| LMArena Hard Prompts | 1448 | 1447 |
| DTBench | 82.7% | 78.9% |
| LMCA | 39.3% | 33.7% |
| Surface Evolver Bench | 30.6% | 55% |
| Epoch Capabilities Index | 142.74 | 147 |
| SimpleBench | — | 45.8% |
| Kagi LLM Benchmark | 63.5% | — |
| Thematic Generalization | 53% | — |
| Mystery Game Puzzles | — | 8% |
| ForecastBench | — | 61.4 |

## Math

- Gemma 4 31B IT: 41.3 (#72)
- MiniMax-M3: 39.1 (#83)

| Benchmark | Gemma 4 31B IT | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 71.1% |
| LMArena Math | 1464 | 1432 |
| ProofBench | — | 18% |

## Knowledge

- Gemma 4 31B IT: 37.9 (#141)
- MiniMax-M3: 58.4 (#32)

| Benchmark | Gemma 4 31B IT | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 75.8% | 90.9% |
| LMArena Expert | 1465 | 1462 |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |

## Multimodal

- Gemma 4 31B IT: 41.0 (#32)
- MiniMax-M3: 39.5 (#45)

| Benchmark | Gemma 4 31B IT | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1278 | 1254 |
| LMArena Document | 1425 | 1435 |

## Multilingual

- Gemma 4 31B IT: 54.0 (#52)
- MiniMax-M3: 53.2 (#70)

| Benchmark | Gemma 4 31B IT | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1431 | 1420 |
| LMArena Chinese | 1478 | 1465 |
| LMArena French | 1436 | 1445 |
| LMArena Russian | 1462 | 1430 |
| LMArena Spanish | 1443 | 1431 |
| LMArena German | — | 1424 |
| LMArena Japanese | — | 1381 |
| LMArena Korean | — | 1372 |

## Instruction Following

- Gemma 4 31B IT: 75.6 (#58)
- MiniMax-M3: 75.7 (#56)

| Benchmark | Gemma 4 31B IT | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1433 | 1433 |

## Long Context

- Gemma 4 31B IT: 44.2 (#67)
- MiniMax-M3: 44.2 (#68)

| Benchmark | Gemma 4 31B IT | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1446 | 1445 |

## Writing & Preference

- Gemma 4 31B IT: 60.7 (#92)
- MiniMax-M3: 62.3 (#79)

| Benchmark | Gemma 4 31B IT | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1443 | 1433 |
| LMArena Creative Writing | 1416 | 1405 |
| EQ-Bench 4 | 1120 | 1150 |
| LMArena Multi-Turn | 1452 | 1441 |
| EQ-Bench Creative Writing | 1368 | — |

## FAQ

### Is Gemma 4 31B IT better than MiniMax-M3?

Gemma 4 31B IT and MiniMax-M3 score almost the same on the Noometry Index (43.2 vs 43.5), so choose on price, context window or the category you care about most.

### Which is cheaper, Gemma 4 31B IT or MiniMax-M3?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.

### Is Gemma 4 31B IT or MiniMax-M3 better for coding?

They score almost the same on coding (41.9 vs 41.5); test both on your own repository before choosing.

### Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 262K.

### How many benchmarks do Gemma 4 31B IT and MiniMax-M3 share?

29 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and MiniMax-M3 has 41.