# Grok 4.7 vs Step 3.7 Flash

> Grok 4.7 is the stronger model overall, scoring 53.1 to 37.3 on the Noometry Index. Step 3.7 Flash costs 7.2× 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-3-7-flash
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. Grok 4.7 scores higher in 3 categories and Step 3.7 Flash in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.7 leads 49.1 to 21.6.
- The biggest single-benchmark swing is NYT Connections (extended): 76.8% for Grok 4.7 and 39.7% for Step 3.7 Flash.
- Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $2 / $6 for Grok 4.7.
- Grok 4.7 accepts more context: 500K tokens versus 256K.
- Step 3.7 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.7 | Step 3.7 Flash |
|---|---|---|
| Provider | xAI | StepFun |
| Noometry Index | 53.1 | 37.3 |
| Rank | 37 | 207 |
| Context | 500K | 256K |
| Input $/M | $2 | $0.18 |
| Output $/M | $6 | $1.11 |
| Weights | Proprietary | Open |

## Coding

- Grok 4.7: 58.0 (#18)
- Step 3.7 Flash: 40.0 (#150)

| Benchmark | Grok 4.7 | Step 3.7 Flash |
|---|---|---|
| SciCode | 57.8% | 40% |
| FrontierCode | 47.6% | — |
| CursorBench | 46.3% | — |
| LMArena WebDev | 1639 | — |
| FrontierSWE | 29.5% | — |
| LMArena Coding | 1427 | — |
| ALE-Bench | — | 694.12 |

## Agentic & Tool Use

- Grok 4.7: 36.7 (#37)
- Step 3.7 Flash: —

| Benchmark | Grok 4.7 | Step 3.7 Flash |
|---|---|---|
| APEX-Agents | 54.6% | — |
| GDP.pdf | 22.8% | — |
| Vending-Bench 2 | 10,537 | — |

## Reasoning

- Grok 4.7: 49.1 (#40)
- Step 3.7 Flash: 21.6 (#219)

| Benchmark | Grok 4.7 | Step 3.7 Flash |
|---|---|---|
| NYT Connections (extended) | 76.8% | 39.7% |
| CritPt | 18% | 2.3% |
| Chess Puzzles | 38% | — |
| LMArena Hard Prompts | 1413 | — |
| Mystery Game Puzzles | 29% | — |
| DTBench | 96% | — |
| LMCA | 49.4% | — |
| Epoch Capabilities Index | 153.53 | — |

## Math

- Grok 4.7: 57.8 (#39)
- Step 3.7 Flash: 42.9 (#82)

| Benchmark | Grok 4.7 | Step 3.7 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 53% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | — | 68.5% |
| OTIS Mock AIME 2024-2025 | 98.1% | — |
| ProofBench | 34% | — |
| LMArena Math | 1407 | — |

## Knowledge

- Grok 4.7: 62.8 (#22)
- Step 3.7 Flash: —

| Benchmark | Grok 4.7 | Step 3.7 Flash |
|---|---|---|
| GPQA Diamond | 92.7% | — |
| SimpleQA Verified | 56% | — |
| LMArena Expert | 1422 | — |

## Multimodal

- Grok 4.7: 35.5 (#87)
- Step 3.7 Flash: —

| Benchmark | Grok 4.7 | Step 3.7 Flash |
|---|---|---|
| LMArena Vision | 1228 | — |
| Blueprint-Bench 2 | 32.5% | — |
| Furniture Assembly | 20.8% | — |

## Multilingual

- Grok 4.7: 50.8 (#116)
- Step 3.7 Flash: —

| Benchmark | Grok 4.7 | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1389 | — |
| LMArena Chinese | 1455 | — |
| LMArena French | 1455 | — |
| LMArena Russian | 1397 | — |
| LMArena Spanish | 1400 | — |

## Instruction Following

- Grok 4.7: 74.1 (#105)
- Step 3.7 Flash: —

| Benchmark | Grok 4.7 | Step 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1404 | — |

## Long Context

- Grok 4.7: 43.1 (#104)
- Step 3.7 Flash: —

| Benchmark | Grok 4.7 | Step 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1413 | — |

## Writing & Preference

- Grok 4.7: 70.0 (#24)
- Step 3.7 Flash: —

| Benchmark | Grok 4.7 | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1399 | — |
| LMArena Creative Writing | 1391 | — |
| EQ-Bench Creative Writing | 2007 | — |
| LMArena Multi-Turn | 1393 | — |

## FAQ

### Is Grok 4.7 better than Step 3.7 Flash?

Grok 4.7 is the stronger model overall, scoring 53.1 to 37.3 on the Noometry Index. Step 3.7 Flash costs 7.2× 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 3.7 Flash?

Step 3.7 Flash is cheaper. It lists at $0.18 per million input tokens and $1.11 per million output tokens; Grok 4.7 lists at $2 and $6.

### Is Grok 4.7 or Step 3.7 Flash better for coding?

Grok 4.7 scores higher on coding benchmarks: 58.0 versus 40.0 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 3.7 Flash share?

3 benchmarks have published results for both models. Grok 4.7 has 39 scored results on Noometry and Step 3.7 Flash has 5.