# Grok 4.7 vs Step 3.5 Flash

> Grok 4.7 is the stronger model overall, scoring 46.6 to 41.7 on the Noometry Index. Step 3.5 Flash costs 20× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/grok-4-7-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Grok 4.7 scores higher in 7 categories and Step 3.5 Flash in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.7 leads 40.1 to 21.2.
- The biggest single-benchmark swing is NYT Connections (extended): 76.8% for Grok 4.7 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 $2 / $6 for Grok 4.7.
- Grok 4.7 accepts more context: 500K tokens versus 256K.
- Step 3.5 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.7 | Step 3.5 Flash |
|---|---|---|
| Provider | xAI | StepFun |
| Noometry Index | 46.6 | 41.7 |
| Rank | 56 | 116 |
| Context | 500K | 256K |
| Input $/M | $2 | $0.10 |
| Output $/M | $6 | $0.30 |
| Weights | Proprietary | Open |

## Coding

- Grok 4.7: 55.0 (#23)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | Grok 4.7 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1423 | 1436 |
| CursorBench | 46.3% | — |
| LMArena WebDev | 1636 | — |
| FrontierSWE | 29.5% | — |
| SciCode | 57.4% | — |

## Reasoning

- Grok 4.7: 40.1 (#49)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | Grok 4.7 | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | 76.8% | 28.4% |
| LMArena Hard Prompts | 1409 | 1411 |
| CritPt | 17.7% | — |

## Math

- Grok 4.7: 41.1 (#73)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | Grok 4.7 | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1393 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| ProofBench | 34% | — |

## Knowledge

- Grok 4.7: 38.7 (#130)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | Grok 4.7 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1413 | 1422 |

## Multimodal

- Grok 4.7: 28.8 (#107)
- Step 3.5 Flash: —

| Benchmark | Grok 4.7 | Step 3.5 Flash |
|---|---|---|
| Furniture Assembly | 20.8% | — |

## Multilingual

- Grok 4.7: 51.2 (#108)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | Grok 4.7 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1392 | 1386 |
| LMArena Chinese | 1476 | 1448 |
| LMArena Russian | 1396 | 1385 |
| LMArena French | — | 1421 |
| LMArena German | — | 1404 |
| LMArena Japanese | — | 1353 |
| LMArena Korean | — | 1350 |
| LMArena Spanish | — | 1419 |

## Instruction Following

- Grok 4.7: 74.3 (#98)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | Grok 4.7 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1406 | 1385 |

## Long Context

- Grok 4.7: 43.2 (#97)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | Grok 4.7 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1416 | 1402 |

## Writing & Preference

- Grok 4.7: 70.1 (#23)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | Grok 4.7 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1397 | 1403 |
| LMArena Creative Writing | 1391 | 1357 |
| LMArena Multi-Turn | 1389 | 1405 |
| EQ-Bench Creative Writing | 2007 | — |

## FAQ

### Is Grok 4.7 better than Step 3.5 Flash?

Grok 4.7 is the stronger model overall, scoring 46.6 to 41.7 on the Noometry Index. Step 3.5 Flash costs 20× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.

### Which is cheaper, Grok 4.7 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; Grok 4.7 lists at $2 and $6.

### Is Grok 4.7 or Step 3.5 Flash better for coding?

Grok 4.7 scores higher on coding benchmarks: 55.0 versus 41.7 in the Noometry coding category.

### Which has the bigger context window?

Grok 4.7 does, with 500K tokens against 256K.

### How many benchmarks do Grok 4.7 and Step 3.5 Flash share?

13 benchmarks have published results for both models. Grok 4.7 has 21 scored results on Noometry and Step 3.5 Flash has 19.