# Gemma 3 27B vs MiniMax-M2

> MiniMax-M2 is the stronger model overall, scoring 37.4 to 30.8 on the Noometry Index. Gemma 3 27B costs 5.2× less per token, which makes it the better buy when MiniMax-M2's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-3-27b-vs-minimax-m2
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Gemma 3 27B scores higher in 2 categories and MiniMax-M2 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2 leads 39.3 to 22.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 40.4% for Gemma 3 27B and 57.8% for MiniMax-M2.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.
- MiniMax-M2 accepts more context: 205K tokens versus 131K.

## Snapshot

| | Gemma 3 27B | MiniMax-M2 |
|---|---|---|
| Provider | Google | MiniMax |
| Noometry Index | 30.8 | 37.4 |
| Rank | 284 | 204 |
| Context | 131K | 205K |
| Input $/M | $0.08 | $0.30 |
| Output $/M | $0.16 | $1.20 |
| Weights | Open | Open |

## Coding

- Gemma 3 27B: 22.5 (#334)
- MiniMax-M2: 39.3 (#159)

| Benchmark | Gemma 3 27B | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1322 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| Aider Polyglot | 4.9% | — |
| LMArena WebDev | — | 1297 |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |

## Agentic & Tool Use

- Gemma 3 27B: 25.1 (#110)
- MiniMax-M2: 25.1 (#109)

| Benchmark | Gemma 3 27B | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Berkeley Function Calling Leaderboard | 29.5% | — |
| Vending-Bench 2 | — | 160.6 |

## Reasoning

- Gemma 3 27B: 16.7 (#301)
- MiniMax-M2: 19.4 (#258)

| Benchmark | Gemma 3 27B | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | 40.4% | 57.8% |
| LMArena Hard Prompts | 1340 | 1357 |
| NYT Connections (extended) | — | 14.8% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |

## Math

- Gemma 3 27B: 25.9 (#265)
- MiniMax-M2: 37.3 (#160)

| Benchmark | Gemma 3 27B | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1312 | 1352 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |

## Knowledge

- Gemma 3 27B: 25.5 (#261)
- MiniMax-M2: 37.0 (#163)

| Benchmark | Gemma 3 27B | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1304 | 1337 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |

## Multimodal

- Gemma 3 27B: 32.6 (#100)
- MiniMax-M2: —

| Benchmark | Gemma 3 27B | MiniMax-M2 |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |

## Multilingual

- Gemma 3 27B: 46.9 (#155)
- MiniMax-M2: 45.3 (#171)

| Benchmark | Gemma 3 27B | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1334 | 1313 |
| LMArena Chinese | 1346 | 1366 |
| LMArena French | 1368 | 1335 |
| LMArena German | 1362 | 1355 |
| LMArena Russian | 1349 | 1331 |
| LMArena Spanish | 1349 | 1326 |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1308 | — |

## Instruction Following

- Gemma 3 27B: 70.6 (#160)
- MiniMax-M2: 70.2 (#166)

| Benchmark | Gemma 3 27B | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1321 | 1328 |
| LiveBench Instruction Following | 74.9% | — |

## Long Context

- Gemma 3 27B: 27.6 (#293)
- MiniMax-M2: 40.5 (#153)

| Benchmark | Gemma 3 27B | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1333 | 1331 |
| Fiction.LiveBench | 33.3% | — |

## Writing & Preference

- Gemma 3 27B: 52.5 (#168)
- MiniMax-M2: 53.0 (#162)

| Benchmark | Gemma 3 27B | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1358 | 1340 |
| LMArena Creative Writing | 1346 | 1286 |
| LMArena Multi-Turn | 1345 | 1361 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |

## FAQ

### Is Gemma 3 27B better than MiniMax-M2?

MiniMax-M2 is the stronger model overall, scoring 37.4 to 30.8 on the Noometry Index. Gemma 3 27B costs 5.2× less per token, which makes it the better buy when MiniMax-M2's lead doesn't matter for your workload.

### Which is cheaper, Gemma 3 27B or MiniMax-M2?

Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.

### Is Gemma 3 27B or MiniMax-M2 better for coding?

MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 22.5 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2 does, with 205K tokens against 131K.

### How many benchmarks do Gemma 3 27B and MiniMax-M2 share?

16 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and MiniMax-M2 has 21.