# MiniMax-M2.1 vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 41.7 to 38.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-1-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. MiniMax-M2.1 scores higher in 2 categories and Step 3.5 Flash in 6 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3.5 Flash leads 21.2 to 15.8.
- The biggest single-benchmark swing is NYT Connections (extended): 11.2% for MiniMax-M2.1 and 28.4% for Step 3.5 Flash.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
- Step 3.5 Flash accepts more context: 256K tokens versus 205K.

## Snapshot

| | MiniMax-M2.1 | Step 3.5 Flash |
|---|---|---|
| Provider | MiniMax | StepFun |
| Noometry Index | 38.4 | 41.7 |
| Rank | 177 | 116 |
| Context | 205K | 256K |
| Input $/M | $0.30 | $0.10 |
| Output $/M | $1.20 | $0.30 |
| Weights | Open | Open |

## Coding

- MiniMax-M2.1: 40.1 (#132)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | MiniMax-M2.1 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1421 | 1436 |
| LMArena WebDev | 1384 | — |
| ALE-Bench | 623.83 | — |

## Agentic & Tool Use

- MiniMax-M2.1: 27.7 (#91)
- Step 3.5 Flash: —

| Benchmark | MiniMax-M2.1 | Step 3.5 Flash |
|---|---|---|
| Terminal-Bench | 36.6% | — |

## Reasoning

- MiniMax-M2.1: 15.8 (#301)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | MiniMax-M2.1 | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | 11.2% | 28.4% |
| LMArena Hard Prompts | 1410 | 1411 |

## Math

- MiniMax-M2.1: 35.6 (#142)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | MiniMax-M2.1 | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1396 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |

## Knowledge

- MiniMax-M2.1: 37.7 (#143)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | MiniMax-M2.1 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1432 | 1422 |
| Vectara Hallucination Rate | 11.8% | — |

## Multilingual

- MiniMax-M2.1: 50.2 (#123)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | MiniMax-M2.1 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1378 | 1386 |
| LMArena Chinese | 1430 | 1448 |
| LMArena French | 1405 | 1421 |
| LMArena German | 1380 | 1404 |
| LMArena Japanese | 1287 | 1353 |
| LMArena Korean | 1297 | 1350 |
| LMArena Russian | 1386 | 1385 |
| LMArena Spanish | 1396 | 1419 |

## Instruction Following

- MiniMax-M2.1: 74.0 (#108)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | MiniMax-M2.1 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1399 | 1385 |

## Long Context

- MiniMax-M2.1: 43.2 (#98)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | MiniMax-M2.1 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1416 | 1402 |

## Writing & Preference

- MiniMax-M2.1: 58.5 (#114)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | MiniMax-M2.1 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1392 | 1403 |
| LMArena Creative Writing | 1362 | 1357 |
| LMArena Multi-Turn | 1396 | 1405 |

## FAQ

### Is MiniMax-M2.1 better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 38.4 on the Noometry Index.

### Which is cheaper, MiniMax-M2.1 or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.

### Is MiniMax-M2.1 or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 40.1 in the Noometry coding category.

### Which has the bigger context window?

Step 3.5 Flash does, with 256K tokens against 205K.

### How many benchmarks do MiniMax-M2.1 and Step 3.5 Flash share?

18 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Step 3.5 Flash has 19.