# Grok Build 0.1 vs Step 3

> Step 3 is the stronger model overall, scoring 40.5 to 36.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-build-0-1-vs-step-3
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Grok Build 0.1 leads 32.2 to 28.4.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Grok Build 0.1 | Step 3 |
|---|---|---|
| Provider | xAI | StepFun |
| Noometry Index | 36.4 | 40.5 |
| Rank | 216 | 149 |
| Context | 256K | — |
| Input $/M | $1 | — |
| Output $/M | $2 | — |
| Weights | Proprietary | Open |

## Coding

- Grok Build 0.1: 43.1 (#91)
- Step 3: 40.1 (#147)

| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| SciCode | 50.2% | — |
| LMArena Coding | — | 1367 |

## Agentic & Tool Use

- Grok Build 0.1: 22.7 (#129)
- Step 3: —

| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| GBAEval | 2.4% | — |

## Reasoning

- Grok Build 0.1: 32.2 (#77)
- Step 3: 28.4 (#105)

| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | — | 62.3% |
| CritPt | 9.1% | — |
| LMArena Hard Prompts | — | 1355 |

## Math

- Grok Build 0.1: —
- Step 3: 37.6 (#148)

| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| LMArena Math | — | 1366 |

## Knowledge

- Grok Build 0.1: —
- Step 3: 36.8 (#164)

| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| LMArena Expert | — | 1333 |

## Multimodal

- Grok Build 0.1: —
- Step 3: 35.5 (#86)

| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |

## Multilingual

- Grok Build 0.1: —
- Step 3: 46.3 (#159)

| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1397 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1371 |

## Instruction Following

- Grok Build 0.1: —
- Step 3: 70.4 (#164)

| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |

## Long Context

- Grok Build 0.1: —
- Step 3: 40.3 (#157)

| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |

## Writing & Preference

- Grok Build 0.1: —
- Step 3: 54.3 (#151)

| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| LMArena Text | — | 1350 |
| LMArena Creative Writing | — | 1321 |
| LMArena Multi-Turn | — | 1341 |

## FAQ

### Is Grok Build 0.1 better than Step 3?

Step 3 is the stronger model overall, scoring 40.5 to 36.4 on the Noometry Index.

### Is Grok Build 0.1 or Step 3 better for coding?

Grok Build 0.1 scores higher on coding benchmarks: 43.1 versus 40.1 in the Noometry coding category.

### How many benchmarks do Grok Build 0.1 and Step 3 share?

0 benchmarks have published results for both models. Grok Build 0.1 has 3 scored results on Noometry and Step 3 has 17.