# Gemini 3.1 Flash Lite vs MiniMax-M2.7

> Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.4 to 37.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-1-flash-lite-vs-minimax-m2-7
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 6 categories and MiniMax-M2.7 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3.1 Flash Lite leads 39.5 to 24.9.
- The biggest single-benchmark swing is Thematic Generalization: 63.3% for Gemini 3.1 Flash Lite and 39.3% for MiniMax-M2.7.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.25 / $1.50 for Gemini 3.1 Flash Lite.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 205K.
- MiniMax-M2.7 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.1 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| Provider | Google | MiniMax |
| Noometry Index | 40.4 | 37.4 |
| Rank | 141 | 188 |
| Context | 1.05M | 205K |
| Input $/M | $0.25 | $0.30 |
| Output $/M | $1.50 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.1 Flash Lite: 37.5 (#179)
- MiniMax-M2.7: 41.4 (#115)

| Benchmark | Gemini 3.1 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| LMArena WebDev | 1256 | 1397 |
| SciCode | 41.9% | 47% |
| WeirdML | 52.2% | 37% |
| LMArena Coding | 1400 | 1454 |
| ALE-Bench | 797.73 | 599.25 |

## Agentic & Tool Use

- Gemini 3.1 Flash Lite: 29.9 (#72)
- MiniMax-M2.7: 24.9 (#103)

| Benchmark | Gemini 3.1 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| DeepResearch Bench | 37.3% | — |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |

## Reasoning

- Gemini 3.1 Flash Lite: 22.3 (#181)
- MiniMax-M2.7: 19.0 (#248)

| Benchmark | Gemini 3.1 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| NYT Connections (extended) | 8.2% | 24.7% |
| CritPt | 1.1% | 0.6% |
| Thematic Generalization | 63.3% | 39.3% |
| LMArena Hard Prompts | 1407 | 1422 |
| Epoch Capabilities Index | 144.45 | 145.84 |
| Kagi LLM Benchmark | 67.2% | — |
| Chess Puzzles | 25% | — |
| EnigmaEval | 3% | — |
| DTBench | 76.8% | — |
| LMCA | 35% | — |
| ForecastBench | 54.4 | — |

## Math

- Gemini 3.1 Flash Lite: 39.5 (#82)
- MiniMax-M2.7: 24.9 (#254)

| Benchmark | Gemini 3.1 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1427 | 1420 |
| FrontierMath (Tiers 1-3) | 27.7% | — |
| OTIS Mock AIME 2024-2025 | 80% | — |
| ProofBench | — | 3% |

## Knowledge

- Gemini 3.1 Flash Lite: 41.7 (#95)
- MiniMax-M2.7: 37.1 (#151)

| Benchmark | Gemini 3.1 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| Vectara Hallucination Rate | 8.2% | 12.9% |
| LMArena Expert | 1397 | 1443 |
| GPQA Diamond | 81.8% | — |
| Humanity's Last Exam | 8.6% | — |

## Multimodal

- Gemini 3.1 Flash Lite: 38.7 (#57)
- MiniMax-M2.7: —

| Benchmark | Gemini 3.1 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| LMArena Vision | 1240 | — |

## Multilingual

- Gemini 3.1 Flash Lite: 52.5 (#82)
- MiniMax-M2.7: 50.5 (#120)

| Benchmark | Gemini 3.1 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1410 | 1382 |
| LMArena Chinese | 1461 | 1439 |
| LMArena French | 1423 | 1422 |
| LMArena German | 1429 | 1398 |
| LMArena Japanese | 1411 | 1261 |
| LMArena Korean | 1393 | 1313 |
| LMArena Russian | 1420 | 1383 |
| LMArena Spanish | 1420 | 1403 |

## Instruction Following

- Gemini 3.1 Flash Lite: 72.9 (#126)
- MiniMax-M2.7: 74.2 (#101)

| Benchmark | Gemini 3.1 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1376 | 1404 |

## Long Context

- Gemini 3.1 Flash Lite: 42.5 (#117)
- MiniMax-M2.7: 43.3 (#94)

| Benchmark | Gemini 3.1 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1394 | 1419 |

## Writing & Preference

- Gemini 3.1 Flash Lite: 61.0 (#90)
- MiniMax-M2.7: 59.1 (#107)

| Benchmark | Gemini 3.1 Flash Lite | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1416 | 1404 |
| LMArena Creative Writing | 1401 | 1354 |
| LMArena Multi-Turn | 1417 | 1413 |

## FAQ

### Is Gemini 3.1 Flash Lite better than MiniMax-M2.7?

Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.4 to 37.4 on the Noometry Index.

### Which is cheaper, Gemini 3.1 Flash Lite 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 3.1 Flash Lite lists at $0.25 and $1.50.

### Is Gemini 3.1 Flash Lite or MiniMax-M2.7 better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.4 versus 37.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.1 Flash Lite does, with 1.05M tokens against 205K.

### How many benchmarks do Gemini 3.1 Flash Lite and MiniMax-M2.7 share?

26 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and MiniMax-M2.7 has 30.