# Gemini 3.8 Flash vs MiniMax-M2.5

> Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 38.1 on the Noometry Index. MiniMax-M2.5 costs 2.9× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-8-flash-vs-minimax-m2-5
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 9 categories and MiniMax-M2.5 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 64.7 to 17.6.
- The biggest single-benchmark swing is NYT Connections (extended): 97.4% for Gemini 3.8 Flash and 16.8% for MiniMax-M2.5.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 205K.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.8 Flash | MiniMax-M2.5 |
|---|---|---|
| Provider | Google | MiniMax |
| Noometry Index | 59.5 | 38.1 |
| Rank | 13 | 181 |
| Context | 1.05M | 205K |
| Input $/M | $0.75 | $0.30 |
| Output $/M | $3.75 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.8 Flash: 56.4 (#17)
- MiniMax-M2.5: 47.9 (#53)

| Benchmark | Gemini 3.8 Flash | MiniMax-M2.5 |
|---|---|---|
| LMArena WebDev | 1581 | 1386 |
| LMArena Coding | 1512 | 1380 |
| ALE-Bench | 1,270 | 618.17 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| SWE-bench Verified (bash only) | — | 75.8% |
| CursorBench | 39.6% | — |
| SWE-bench Multilingual | — | 68.3% |
| FrontierSWE | 19.6% | — |
| SciCode | 56.6% | — |

## Agentic & Tool Use

- Gemini 3.8 Flash: 40.3 (#22)
- MiniMax-M2.5: 30.2 (#70)

| Benchmark | Gemini 3.8 Flash | MiniMax-M2.5 |
|---|---|---|
| Vending-Bench 2 | 5,094 | -23.16 |
| Terminal-Bench | — | 42.7% |
| APEX-Agents | 64.3% | — |
| GDP.pdf | 23.4% | — |

## Reasoning

- Gemini 3.8 Flash: 64.7 (#13)
- MiniMax-M2.5: 17.6 (#281)

| Benchmark | Gemini 3.8 Flash | MiniMax-M2.5 |
|---|---|---|
| NYT Connections (extended) | 97.4% | 16.8% |
| LMArena Hard Prompts | 1506 | 1372 |
| Epoch Capabilities Index | 157.13 | 146.68 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | 18.3% | — |
| Chess Puzzles | 61% | — |
| Mystery Game Puzzles | 47% | — |
| DTBench | 95.7% | — |
| LMCA | 52.9% | — |
| Surface Evolver Bench | 76.9% | — |

## Math

- Gemini 3.8 Flash: 65.2 (#22)
- MiniMax-M2.5: 25.8 (#242)

| Benchmark | Gemini 3.8 Flash | MiniMax-M2.5 |
|---|---|---|
| ProofBench | 48% | 4% |
| LMArena Math | 1528 | 1378 |
| FrontierMath (Tiers 1-3) | 68.4% | — |
| FrontierMath Tier 4 | 22% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |

## Knowledge

- Gemini 3.8 Flash: 74.9 (#2)
- MiniMax-M2.5: 38.6 (#132)

| Benchmark | Gemini 3.8 Flash | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1529 | 1378 |
| GPQA Diamond | 95.4% | — |
| Humanity's Last Exam | 44.5% | — |
| SimpleQA Verified | 69.7% | — |
| Vectara Hallucination Rate | — | 9.1% |

## Multimodal

- Gemini 3.8 Flash: 40.9 (#33)
- MiniMax-M2.5: —

| Benchmark | Gemini 3.8 Flash | MiniMax-M2.5 |
|---|---|---|
| LMArena Vision | 1312 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |

## Multilingual

- Gemini 3.8 Flash: 57.9 (#5)
- MiniMax-M2.5: 47.3 (#147)

| Benchmark | Gemini 3.8 Flash | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1486 | 1338 |
| LMArena Chinese | 1547 | 1392 |
| LMArena French | 1502 | 1363 |
| LMArena German | 1470 | 1361 |
| LMArena Japanese | 1505 | 1169 |
| LMArena Korean | 1479 | 1232 |
| LMArena Russian | 1507 | 1359 |
| LMArena Spanish | 1492 | 1354 |

## Instruction Following

- Gemini 3.8 Flash: 78.2 (#11)
- MiniMax-M2.5: 71.7 (#143)

| Benchmark | Gemini 3.8 Flash | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1489 | 1353 |

## Long Context

- Gemini 3.8 Flash: 46.2 (#23)
- MiniMax-M2.5: 37.4 (#211)

| Benchmark | Gemini 3.8 Flash | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1506 | 1367 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |

## Writing & Preference

- Gemini 3.8 Flash: 72.1 (#16)
- MiniMax-M2.5: 54.1 (#149)

| Benchmark | Gemini 3.8 Flash | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1494 | 1359 |
| LMArena Creative Writing | 1485 | 1331 |
| EQ-Bench Creative Writing | 1748 | 1361 |
| LMArena Multi-Turn | 1503 | 1364 |

## FAQ

### Is Gemini 3.8 Flash better than MiniMax-M2.5?

Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 38.1 on the Noometry Index. MiniMax-M2.5 costs 2.9× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.8 Flash 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 3.8 Flash lists at $0.75 and $3.75.

### Is Gemini 3.8 Flash or MiniMax-M2.5 better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 56.4 versus 47.9 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 205K.

### How many benchmarks do Gemini 3.8 Flash and MiniMax-M2.5 share?

24 benchmarks have published results for both models. Gemini 3.8 Flash has 46 scored results on Noometry and MiniMax-M2.5 has 33.