# Gemma 2 9B vs MiniMax-M2.5

> MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-9b-vs-minimax-m2-5
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and MiniMax-M2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.5 leads 39.2 to 9.7.

## Snapshot

| | Gemma 2 9B | MiniMax-M2.5 |
|---|---|---|
| Provider | Google | MiniMax |
| Noometry Index | 25.9 | 38.3 |
| Rank | 341 | 188 |
| Context | — | 205K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Open | Open |

## Coding

- Gemma 2 9B: 29.4 (#304)
- MiniMax-M2.5: 48.1 (#58)

| Benchmark | Gemma 2 9B | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1173 | 1381 |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1387 |
| SWE-bench Multilingual | — | 68.3% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
| ALE-Bench | — | 618.17 |

## Agentic & Tool Use

- Gemma 2 9B: —
- MiniMax-M2.5: 30.4 (#77)

| Benchmark | Gemma 2 9B | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Vending-Bench 2 | — | -23.16 |

## Reasoning

- Gemma 2 9B: 15.9 (#309)
- MiniMax-M2.5: 17.5 (#292)

| Benchmark | Gemma 2 9B | MiniMax-M2.5 |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1372 |
| Epoch Capabilities Index | 119.83 | 146.68 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |

## Math

- Gemma 2 9B: 9.9 (#318)
- MiniMax-M2.5: 26.9 (#253)

| Benchmark | Gemma 2 9B | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1183 | 1378 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| ProofBench | — | 4% |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |

## Knowledge

- Gemma 2 9B: 9.7 (#305)
- MiniMax-M2.5: 39.2 (#135)

| Benchmark | Gemma 2 9B | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1147 | 1379 |
| GPQA Diamond | 27.5% | — |
| Vectara Hallucination Rate | — | 9.1% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |

## Multilingual

- Gemma 2 9B: 36.6 (#238)
- MiniMax-M2.5: 47.1 (#152)

| Benchmark | Gemma 2 9B | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1188 | 1338 |
| LMArena Chinese | 1185 | 1393 |
| LMArena French | 1190 | 1362 |
| LMArena German | 1186 | 1362 |
| LMArena Japanese | 1144 | 1171 |
| LMArena Korean | 1137 | 1232 |
| LMArena Russian | 1200 | 1358 |
| LMArena Spanish | 1200 | 1354 |

## Instruction Following

- Gemma 2 9B: 57.6 (#269)
- MiniMax-M2.5: 71.5 (#148)

| Benchmark | Gemma 2 9B | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1178 | 1353 |
| LiveBench Instruction Following | 52.6% | — |

## Long Context

- Gemma 2 9B: 36.3 (#233)
- MiniMax-M2.5: 37.5 (#216)

| Benchmark | Gemma 2 9B | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1197 | 1366 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |

## Writing & Preference

- Gemma 2 9B: 32.1 (#281)
- MiniMax-M2.5: 53.9 (#153)

| Benchmark | Gemma 2 9B | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1207 | 1359 |
| LMArena Creative Writing | 1206 | 1331 |
| EQ-Bench Creative Writing | 841 | 1361 |
| LMArena Multi-Turn | 1193 | 1364 |
| LiveBench Language | 25.5% | — |

## FAQ

### Is Gemma 2 9B better than MiniMax-M2.5?

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 25.9 on the Noometry Index.

### Is Gemma 2 9B 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 2 9B and MiniMax-M2.5 share?

19 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and MiniMax-M2.5 has 33.