# Grok Build 0.1 vs Inkling

> Inkling is the stronger model overall, scoring 44.1 to 36.4 on the Noometry Index. Grok Build 0.1 costs 2.1× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/grok-build-0-1-vs-inkling
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Grok Build 0.1 scores higher in 1 category and Inkling in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Grok Build 0.1 leads 43.1 to 34.5.
- Grok Build 0.1 is cheaper at $1 / $2 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Grok Build 0.1 accepts more context: 256K tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.

## Snapshot

| | Grok Build 0.1 | Inkling |
|---|---|---|
| Provider | xAI | Thinking Machines Lab |
| Noometry Index | 36.4 | 44.1 |
| Rank | 216 | 80 |
| Context | 256K | 66K |
| Input $/M | $1 | $1.87 |
| Output $/M | $2 | $4.68 |
| Weights | Proprietary | Open |

## Coding

- Grok Build 0.1: 43.1 (#91)
- Inkling: 34.5 (#234)

| Benchmark | Grok Build 0.1 | Inkling |
|---|---|---|
| SciCode | 50.2% | 47% |
| FrontierCode | — | 14% |
| LMArena WebDev | — | 1413 |
| FrontierSWE | — | 4.1% |
| WeirdML | — | 32.3% |
| LMArena Coding | — | 1464 |
| ALE-Bench | — | 946 |

## Agentic & Tool Use

- Grok Build 0.1: 22.7 (#129)
- Inkling: 29.6 (#85)

| Benchmark | Grok Build 0.1 | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |
| GBAEval | 2.4% | — |

## Reasoning

- Grok Build 0.1: 32.2 (#77)
- Inkling: 40.4 (#56)

| Benchmark | Grok Build 0.1 | Inkling |
|---|---|---|
| CritPt | 9.1% | 5.4% |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| ARC-AGI-1 | — | 79.5% |
| Chess Puzzles | — | 21% |
| LMArena Hard Prompts | — | 1451 |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 148.54 |

## Math

- Grok Build 0.1: —
- Inkling: 31.3 (#225)

| Benchmark | Grok Build 0.1 | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 0% |
| LMArena Math | — | 1479 |

## Knowledge

- Grok Build 0.1: —
- Inkling: 55.1 (#49)

| Benchmark | Grok Build 0.1 | Inkling |
|---|---|---|
| GPQA Diamond | — | 88.3% |
| SimpleQA Verified | — | 40.3% |
| LMArena Expert | — | 1465 |

## Multilingual

- Grok Build 0.1: —
- Inkling: 54.0 (#52)

| Benchmark | Grok Build 0.1 | Inkling |
|---|---|---|
| LMArena Non-English | — | 1434 |
| LMArena Chinese | — | 1490 |
| LMArena French | — | 1458 |
| LMArena German | — | 1446 |
| LMArena Japanese | — | 1429 |
| LMArena Korean | — | 1404 |
| LMArena Russian | — | 1429 |
| LMArena Spanish | — | 1448 |

## Instruction Following

- Grok Build 0.1: —
- Inkling: 75.1 (#71)

| Benchmark | Grok Build 0.1 | Inkling |
|---|---|---|
| LMArena Instruction Following | — | 1426 |

## Long Context

- Grok Build 0.1: —
- Inkling: 43.8 (#86)

| Benchmark | Grok Build 0.1 | Inkling |
|---|---|---|
| LMArena Longer Query | — | 1434 |

## Writing & Preference

- Grok Build 0.1: —
- Inkling: 65.2 (#51)

| Benchmark | Grok Build 0.1 | Inkling |
|---|---|---|
| LMArena Text | — | 1441 |
| LMArena Creative Writing | — | 1387 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |
| LMArena Multi-Turn | — | 1436 |

## FAQ

### Is Grok Build 0.1 better than Inkling?

Inkling is the stronger model overall, scoring 44.1 to 36.4 on the Noometry Index. Grok Build 0.1 costs 2.1× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.

### Which is cheaper, Grok Build 0.1 or Inkling?

Grok Build 0.1 is cheaper. It lists at $1 per million input tokens and $2 per million output tokens; Inkling lists at $1.87 and $4.68.

### Is Grok Build 0.1 or Inkling better for coding?

Grok Build 0.1 scores higher on coding benchmarks: 43.1 versus 34.5 in the Noometry coding category.

### Which has the bigger context window?

Grok Build 0.1 does, with 256K tokens against 66K.

### How many benchmarks do Grok Build 0.1 and Inkling share?

2 benchmarks have published results for both models. Grok Build 0.1 has 3 scored results on Noometry and Inkling has 41.