# Gemma 2B vs MiniMax-M2.5

> MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 29.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2b-vs-minimax-m2-5
- Last updated: 2026-10-11
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Gemma 2B scores higher in 2 categories and MiniMax-M2.5 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.5 leads 53.9 to 24.0.

## Snapshot

| | Gemma 2B | MiniMax-M2.5 |
|---|---|---|
| Provider | Google | MiniMax |
| Noometry Index | 29.6 | 38.3 |
| Rank | 307 | 188 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Open | Open |

## Coding

- Gemma 2B: 29.4 (#305)
- MiniMax-M2.5: 48.1 (#58)

| Benchmark | Gemma 2B | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1010 | 1381 |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1387 |
| SWE-bench Multilingual | — | 68.3% |
| ALE-Bench | — | 618.17 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |

## Agentic & Tool Use

- Gemma 2B: —
- MiniMax-M2.5: 30.4 (#77)

| Benchmark | Gemma 2B | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Vending-Bench 2 | — | -23.16 |

## Reasoning

- Gemma 2B: 18.8 (#275)
- MiniMax-M2.5: 17.5 (#292)

| Benchmark | Gemma 2B | MiniMax-M2.5 |
|---|---|---|
| LMArena Hard Prompts | 989 | 1372 |
| Epoch Capabilities Index | 94.2 | 146.68 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| BIG-Bench Hard | 35.2% | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |

## Math

- Gemma 2B: 30.0 (#239)
- MiniMax-M2.5: 26.9 (#253)

| Benchmark | Gemma 2B | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1009 | 1378 |
| ProofBench | — | 4% |
| GSM8K | 17.7% | — |

## Knowledge

- Gemma 2B: —
- MiniMax-M2.5: 39.2 (#135)

| Benchmark | Gemma 2B | MiniMax-M2.5 |
|---|---|---|
| Vectara Hallucination Rate | — | 9.1% |
| LMArena Expert | — | 1379 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |

## Multilingual

- Gemma 2B: 23.0 (#294)
- MiniMax-M2.5: 47.1 (#152)

| Benchmark | Gemma 2B | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 958 | 1338 |
| LMArena Chinese | 986 | 1393 |
| LMArena Russian | 937 | 1358 |
| LMArena French | — | 1362 |
| LMArena German | — | 1362 |
| LMArena Japanese | — | 1171 |
| LMArena Korean | — | 1232 |
| LMArena Spanish | — | 1354 |

## Instruction Following

- Gemma 2B: 48.5 (#302)
- MiniMax-M2.5: 71.5 (#148)

| Benchmark | Gemma 2B | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 970 | 1353 |

## Long Context

- Gemma 2B: 29.9 (#291)
- MiniMax-M2.5: 37.5 (#216)

| Benchmark | Gemma 2B | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 981 | 1366 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |

## Writing & Preference

- Gemma 2B: 24.0 (#308)
- MiniMax-M2.5: 53.9 (#153)

| Benchmark | Gemma 2B | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1002 | 1359 |
| LMArena Creative Writing | 987 | 1331 |
| LMArena Multi-Turn | 945 | 1364 |
| EQ-Bench Creative Writing | — | 1361 |

## FAQ

### Is Gemma 2B better than MiniMax-M2.5?

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 29.6 on the Noometry Index.

### Is Gemma 2B or MiniMax-M2.5 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 29.4 in the Noometry coding category.

### How many benchmarks do Gemma 2B and MiniMax-M2.5 share?

12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and MiniMax-M2.5 has 33.