# Gemma 7B vs MiniMax-M2.7

> MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-7b-vs-minimax-m2-7
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Gemma 7B scores higher in 2 categories and MiniMax-M2.7 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.7 leads 59.1 to 27.2.

## Snapshot

| | Gemma 7B | MiniMax-M2.7 |
|---|---|---|
| Provider | Google | MiniMax |
| Noometry Index | 29.5 | 37.4 |
| Rank | 295 | 188 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Open | Open |

## Coding

- Gemma 7B: 29.9 (#290)
- MiniMax-M2.7: 41.4 (#115)

| Benchmark | Gemma 7B | MiniMax-M2.7 |
|---|---|---|
| LMArena Coding | 1048 | 1454 |
| LMArena WebDev | — | 1397 |
| SciCode | — | 47% |
| WeirdML | — | 37% |
| ALE-Bench | — | 599.25 |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |

## Agentic & Tool Use

- Gemma 7B: —
- MiniMax-M2.7: 24.9 (#103)

| Benchmark | Gemma 7B | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |

## Reasoning

- Gemma 7B: 19.0 (#247)
- MiniMax-M2.7: 19.0 (#248)

| Benchmark | Gemma 7B | MiniMax-M2.7 |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1422 |
| Epoch Capabilities Index | 111.74 | 145.84 |
| NYT Connections (extended) | — | 24.7% |
| CritPt | — | 0.6% |
| Thematic Generalization | — | 39.3% |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |

## Math

- Gemma 7B: 28.7 (#225)
- MiniMax-M2.7: 24.9 (#254)

| Benchmark | Gemma 7B | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1066 | 1420 |
| ProofBench | — | 3% |
| GSM8K | 46.4% | — |

## Knowledge

- Gemma 7B: 26.8 (#248)
- MiniMax-M2.7: 37.1 (#151)

| Benchmark | Gemma 7B | MiniMax-M2.7 |
|---|---|---|
| LMArena Expert | 1002 | 1443 |
| Vectara Hallucination Rate | — | 12.9% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |

## Multilingual

- Gemma 7B: 25.3 (#282)
- MiniMax-M2.7: 50.5 (#120)

| Benchmark | Gemma 7B | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 999 | 1382 |
| LMArena Chinese | 1035 | 1439 |
| LMArena French | 1024 | 1422 |
| LMArena Russian | 993 | 1383 |
| LMArena German | — | 1398 |
| LMArena Japanese | — | 1261 |
| LMArena Korean | — | 1313 |
| LMArena Spanish | — | 1403 |

## Instruction Following

- Gemma 7B: 51.7 (#290)
- MiniMax-M2.7: 74.2 (#101)

| Benchmark | Gemma 7B | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1017 | 1404 |

## Long Context

- Gemma 7B: 31.1 (#277)
- MiniMax-M2.7: 43.3 (#94)

| Benchmark | Gemma 7B | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1022 | 1419 |

## Writing & Preference

- Gemma 7B: 27.2 (#297)
- MiniMax-M2.7: 59.1 (#107)

| Benchmark | Gemma 7B | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1056 | 1404 |
| LMArena Creative Writing | 1024 | 1354 |
| LMArena Multi-Turn | 963 | 1413 |

## FAQ

### Is Gemma 7B better than MiniMax-M2.7?

MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 29.5 on the Noometry Index.

### Is Gemma 7B or MiniMax-M2.7 better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.4 versus 29.9 in the Noometry coding category.

### How many benchmarks do Gemma 7B and MiniMax-M2.7 share?

14 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and MiniMax-M2.7 has 30.