# Gemini 3.1 Pro Preview vs MiniMax-M2.5

> Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 38.3 on the Noometry Index. MiniMax-M2.5 costs 8.6× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-1-pro-preview-vs-minimax-m2-5
- Last updated: 2026-10-10
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and MiniMax-M2.5 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 17.5.
- The biggest single-benchmark swing is NYT Connections (extended): 97.4% for Gemini 3.1 Pro Preview and 16.8% for MiniMax-M2.5.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 205K.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.1 Pro Preview | MiniMax-M2.5 |
|---|---|---|
| Provider | Google | MiniMax |
| Noometry Index | 56.7 | 38.3 |
| Rank | 23 | 188 |
| Context | 1.05M | 205K |
| Input $/M | $2 | $0.30 |
| Output $/M | $12 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.1 Pro Preview: 42.5 (#99)
- MiniMax-M2.5: 48.1 (#58)

| Benchmark | Gemini 3.1 Pro Preview | MiniMax-M2.5 |
|---|---|---|
| LMArena WebDev | 1447 | 1387 |
| LMArena Coding | 1484 | 1381 |
| ALE-Bench | 1,161 | 618.17 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| SWE-bench Verified (bash only) | — | 75.8% |
| SWE-bench Multilingual | — | 68.3% |
| SciCode | 58.9% | — |
| GSO | 22.6% | — |
| WeirdML | 72.1% | — |
| MirrorCode | 8.9% | — |
| AlgoTune | 2.02 | — |

## Agentic & Tool Use

- Gemini 3.1 Pro Preview: 37.7 (#34)
- MiniMax-M2.5: 30.4 (#77)

| Benchmark | Gemini 3.1 Pro Preview | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | 80.2% | 42.7% |
| Vending-Bench 2 | 3,774 | -23.16 |
| APEX-Agents | 35.3% | — |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| BALROG | 57% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| METR Time Horizons | 77% | — |

## Reasoning

- Gemini 3.1 Pro Preview: 71.7 (#12)
- MiniMax-M2.5: 17.5 (#292)

| Benchmark | Gemini 3.1 Pro Preview | MiniMax-M2.5 |
|---|---|---|
| ARC-AGI-2 | 77.1% | 4.9% |
| NYT Connections (extended) | 97.4% | 16.8% |
| ARC-AGI-1 | 98% | 63.7% |
| LMArena Hard Prompts | 1485 | 1372 |
| Epoch Capabilities Index | 154.77 | 146.68 |
| SimpleBench | 79.6% | — |
| Kagi LLM Benchmark | — | 55.2% |
| CritPt | 17.7% | — |
| Chess Puzzles | 55% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.1% | — |
| LMCA | 53.8% | — |
| ForecastBench | 59 | — |

## Math

- Gemini 3.1 Pro Preview: 62.1 (#34)
- MiniMax-M2.5: 26.9 (#253)

| Benchmark | Gemini 3.1 Pro Preview | MiniMax-M2.5 |
|---|---|---|
| ProofBench | 26% | 4% |
| LMArena Math | 1485 | 1378 |
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |

## Knowledge

- Gemini 3.1 Pro Preview: 71.8 (#3)
- MiniMax-M2.5: 39.2 (#135)

| Benchmark | Gemini 3.1 Pro Preview | MiniMax-M2.5 |
|---|---|---|
| Vectara Hallucination Rate | 10.4% | 9.1% |
| LMArena Expert | 1485 | 1379 |
| GPQA Diamond | 94.4% | — |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |

## Multimodal

- Gemini 3.1 Pro Preview: 37.9 (#69)
- MiniMax-M2.5: —

| Benchmark | Gemini 3.1 Pro Preview | MiniMax-M2.5 |
|---|---|---|
| LMArena Vision | 1296 | — |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |

## Multilingual

- Gemini 3.1 Pro Preview: 57.0 (#12)
- MiniMax-M2.5: 47.1 (#152)

| Benchmark | Gemini 3.1 Pro Preview | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1477 | 1338 |
| LMArena Chinese | 1529 | 1393 |
| LMArena French | 1487 | 1362 |
| LMArena German | 1491 | 1362 |
| LMArena Japanese | 1493 | 1171 |
| LMArena Korean | 1455 | 1232 |
| LMArena Russian | 1498 | 1358 |
| LMArena Spanish | 1479 | 1354 |

## Instruction Following

- Gemini 3.1 Pro Preview: 77.0 (#32)
- MiniMax-M2.5: 71.5 (#148)

| Benchmark | Gemini 3.1 Pro Preview | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1466 | 1353 |

## Long Context

- Gemini 3.1 Pro Preview: 47.4 (#18)
- MiniMax-M2.5: 37.5 (#216)

| Benchmark | Gemini 3.1 Pro Preview | MiniMax-M2.5 |
|---|---|---|
| CL-bench | 20.8% | 11.4% |
| CL-bench Life | 16.9% | 6.3% |
| LMArena Longer Query | 1483 | 1366 |

## Writing & Preference

- Gemini 3.1 Pro Preview: 66.1 (#37)
- MiniMax-M2.5: 53.9 (#153)

| Benchmark | Gemini 3.1 Pro Preview | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1481 | 1359 |
| LMArena Creative Writing | 1482 | 1331 |
| EQ-Bench Creative Writing | 1491 | 1361 |
| LMArena Multi-Turn | 1488 | 1364 |
| EQ-Bench 4 | 1142 | — |

## FAQ

### Is Gemini 3.1 Pro Preview better than MiniMax-M2.5?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 38.3 on the Noometry Index. MiniMax-M2.5 costs 8.6× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.1 Pro Preview or MiniMax-M2.5?

MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

### Is Gemini 3.1 Pro Preview or MiniMax-M2.5 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 42.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 205K.

### How many benchmarks do Gemini 3.1 Pro Preview and MiniMax-M2.5 share?

30 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and MiniMax-M2.5 has 33.