# MiniMax-M2.7 vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 41.7 to 37.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-7-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. MiniMax-M2.7 scores higher in 3 categories and Step 3.5 Flash in 5 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3.5 Flash leads 40.6 to 24.9.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.7.
- Step 3.5 Flash accepts more context: 256K tokens versus 205K.

## Snapshot

| | MiniMax-M2.7 | Step 3.5 Flash |
|---|---|---|
| Provider | MiniMax | StepFun |
| Noometry Index | 37.4 | 41.7 |
| Rank | 188 | 116 |
| Context | 205K | 256K |
| Input $/M | $0.30 | $0.10 |
| Output $/M | $1.20 | $0.30 |
| Weights | Open | Open |

## Coding

- MiniMax-M2.7: 41.4 (#115)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | MiniMax-M2.7 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1454 | 1436 |
| LMArena WebDev | 1397 | — |
| SciCode | 47% | — |
| WeirdML | 37% | — |
| ALE-Bench | 599.25 | — |

## Agentic & Tool Use

- MiniMax-M2.7: 24.9 (#103)
- Step 3.5 Flash: —

| Benchmark | MiniMax-M2.7 | Step 3.5 Flash |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |

## Reasoning

- MiniMax-M2.7: 19.0 (#248)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | MiniMax-M2.7 | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | 24.7% | 28.4% |
| LMArena Hard Prompts | 1422 | 1411 |
| CritPt | 0.6% | — |
| Thematic Generalization | 39.3% | — |
| Epoch Capabilities Index | 145.84 | — |

## Math

- MiniMax-M2.7: 24.9 (#254)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | MiniMax-M2.7 | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1420 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| ProofBench | 3% | — |

## Knowledge

- MiniMax-M2.7: 37.1 (#151)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | MiniMax-M2.7 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1443 | 1422 |
| Vectara Hallucination Rate | 12.9% | — |

## Multilingual

- MiniMax-M2.7: 50.5 (#120)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | MiniMax-M2.7 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1382 | 1386 |
| LMArena Chinese | 1439 | 1448 |
| LMArena French | 1422 | 1421 |
| LMArena German | 1398 | 1404 |
| LMArena Japanese | 1261 | 1353 |
| LMArena Korean | 1313 | 1350 |
| LMArena Russian | 1383 | 1385 |
| LMArena Spanish | 1403 | 1419 |

## Instruction Following

- MiniMax-M2.7: 74.2 (#101)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | MiniMax-M2.7 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1404 | 1385 |

## Long Context

- MiniMax-M2.7: 43.3 (#94)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | MiniMax-M2.7 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1419 | 1402 |

## Writing & Preference

- MiniMax-M2.7: 59.1 (#107)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | MiniMax-M2.7 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1404 | 1403 |
| LMArena Creative Writing | 1354 | 1357 |
| LMArena Multi-Turn | 1413 | 1405 |

## FAQ

### Is MiniMax-M2.7 better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 37.4 on the Noometry Index.

### Which is cheaper, MiniMax-M2.7 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-M2.7 lists at $0.30 and $1.20.

### Is MiniMax-M2.7 or Step 3.5 Flash better for coding?

They score almost the same on coding (41.4 vs 41.7); test both on your own repository before choosing.

### Which has the bigger context window?

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

### How many benchmarks do MiniMax-M2.7 and Step 3.5 Flash share?

18 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Step 3.5 Flash has 19.