# Gemini 3.7 Flash vs MiniMax-M2.7

> Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 2.9× less per token, which makes it the better buy when Gemini 3.7 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-7-flash-vs-minimax-m2-7
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Gemini 3.7 Flash scores higher in 9 categories and MiniMax-M2.7 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.1 to 19.0.
- The biggest single-benchmark swing is NYT Connections (extended): 94% for Gemini 3.7 Flash and 24.7% for MiniMax-M2.7.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.7 Flash.
- Gemini 3.7 Flash accepts more context: 1.05M tokens versus 205K.
- MiniMax-M2.7 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.7 Flash | MiniMax-M2.7 |
|---|---|---|
| Provider | Google | MiniMax |
| Noometry Index | 59.8 | 37.4 |
| Rank | 11 | 188 |
| Context | 1.05M | 205K |
| Input $/M | $0.75 | $0.30 |
| Output $/M | $3.75 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.7 Flash: 55.7 (#19)
- MiniMax-M2.7: 41.4 (#115)

| Benchmark | Gemini 3.7 Flash | MiniMax-M2.7 |
|---|---|---|
| LMArena WebDev | 1593 | 1397 |
| SciCode | 59.8% | 47% |
| LMArena Coding | 1499 | 1454 |
| ALE-Bench | 904.3 | 599.25 |
| DeepSWE | 65.5% | — |
| FrontierCode | 43.6% | — |
| FrontierSWE | 20.3% | — |
| WeirdML | — | 37% |

## Agentic & Tool Use

- Gemini 3.7 Flash: 42.2 (#18)
- MiniMax-M2.7: 24.9 (#103)

| Benchmark | Gemini 3.7 Flash | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| APEX-Agents | 67.8% | — |
| Remote Labor Index | 5% | — |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
| GDP.pdf | 23.8% | — |

## Reasoning

- Gemini 3.7 Flash: 70.1 (#12)
- MiniMax-M2.7: 19.0 (#248)

| Benchmark | Gemini 3.7 Flash | MiniMax-M2.7 |
|---|---|---|
| NYT Connections (extended) | 94% | 24.7% |
| CritPt | 14.3% | 0.6% |
| LMArena Hard Prompts | 1497 | 1422 |
| Epoch Capabilities Index | 157.72 | 145.84 |
| ARC-AGI-2 | 84.6% | — |
| ARC-AGI-1 | 95.5% | — |
| Chess Puzzles | 47% | — |
| Thematic Generalization | — | 39.3% |
| Mystery Game Puzzles | 37% | — |
| DTBench | 96.8% | — |
| LMCA | 50.4% | — |

## Math

- Gemini 3.7 Flash: 69.5 (#18)
- MiniMax-M2.7: 24.9 (#254)

| Benchmark | Gemini 3.7 Flash | MiniMax-M2.7 |
|---|---|---|
| ProofBench | 58% | 3% |
| LMArena Math | 1511 | 1420 |
| FrontierMath (Tiers 1-3) | 71.6% | — |
| FrontierMath Tier 4 | 36.6% | — |
| OTIS Mock AIME 2024-2025 | 97.2% | — |

## Knowledge

- Gemini 3.7 Flash: 69.8 (#4)
- MiniMax-M2.7: 37.1 (#151)

| Benchmark | Gemini 3.7 Flash | MiniMax-M2.7 |
|---|---|---|
| LMArena Expert | 1508 | 1443 |
| GPQA Diamond | 94.8% | — |
| SimpleQA Verified | 69.2% | — |
| Vectara Hallucination Rate | — | 12.9% |

## Multimodal

- Gemini 3.7 Flash: 36.9 (#69)
- MiniMax-M2.7: —

| Benchmark | Gemini 3.7 Flash | MiniMax-M2.7 |
|---|---|---|
| LMArena Vision | 1314 | — |
| Furniture Assembly | 26.7% | — |

## Multilingual

- Gemini 3.7 Flash: 57.8 (#7)
- MiniMax-M2.7: 50.5 (#120)

| Benchmark | Gemini 3.7 Flash | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1485 | 1382 |
| LMArena Chinese | 1553 | 1439 |
| LMArena French | 1512 | 1422 |
| LMArena German | 1485 | 1398 |
| LMArena Japanese | 1506 | 1261 |
| LMArena Korean | 1486 | 1313 |
| LMArena Russian | 1519 | 1383 |
| LMArena Spanish | 1507 | 1403 |

## Instruction Following

- Gemini 3.7 Flash: 78.0 (#12)
- MiniMax-M2.7: 74.2 (#101)

| Benchmark | Gemini 3.7 Flash | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1486 | 1404 |

## Long Context

- Gemini 3.7 Flash: 45.8 (#28)
- MiniMax-M2.7: 43.3 (#94)

| Benchmark | Gemini 3.7 Flash | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1493 | 1419 |

## Writing & Preference

- Gemini 3.7 Flash: 71.4 (#19)
- MiniMax-M2.7: 59.1 (#107)

| Benchmark | Gemini 3.7 Flash | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1487 | 1404 |
| LMArena Creative Writing | 1490 | 1354 |
| LMArena Multi-Turn | 1495 | 1413 |
| EQ-Bench Creative Writing | 1723 | — |

## FAQ

### Is Gemini 3.7 Flash better than MiniMax-M2.7?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 2.9× less per token, which makes it the better buy when Gemini 3.7 Flash's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.7 Flash or MiniMax-M2.7?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Gemini 3.7 Flash lists at $0.75 and $3.75.

### Is Gemini 3.7 Flash or MiniMax-M2.7 better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 55.7 versus 41.4 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.7 Flash does, with 1.05M tokens against 205K.

### How many benchmarks do Gemini 3.7 Flash and MiniMax-M2.7 share?

24 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and MiniMax-M2.7 has 30.