# Grok 4.7 vs Inkling

> Grok 4.7 is the stronger model overall, scoring 46.6 to 44.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-7-vs-inkling
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Grok 4.7 scores higher in 3 categories and Inkling in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Grok 4.7 leads 55.0 to 34.1.
- The biggest single-benchmark swing is ProofBench: 34% for Grok 4.7 and 0% for Inkling.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $2 / $6 for Grok 4.7.
- Grok 4.7 accepts more context: 500K tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.7 | Inkling |
|---|---|---|
| Provider | xAI | Thinking Machines Lab |
| Noometry Index | 46.6 | 44.1 |
| Rank | 56 | 75 |
| Context | 500K | 66K |
| Input $/M | $2 | $1.87 |
| Output $/M | $6 | $4.68 |
| Weights | Proprietary | Open |

## Coding

- Grok 4.7: 55.0 (#23)
- Inkling: 34.1 (#229)

| Benchmark | Grok 4.7 | Inkling |
|---|---|---|
| LMArena WebDev | 1636 | 1412 |
| FrontierSWE | 29.5% | 4.1% |
| SciCode | 57.4% | 47% |
| LMArena Coding | 1423 | 1463 |
| FrontierCode | — | 14% |
| CursorBench | 46.3% | — |
| WeirdML | — | 32.3% |
| ALE-Bench | — | 946 |

## Agentic & Tool Use

- Grok 4.7: —
- Inkling: 29.5 (#76)

| Benchmark | Grok 4.7 | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |

## Reasoning

- Grok 4.7: 40.1 (#49)
- Inkling: 40.6 (#48)

| Benchmark | Grok 4.7 | Inkling |
|---|---|---|
| CritPt | 17.7% | 5.4% |
| LMArena Hard Prompts | 1409 | 1452 |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| NYT Connections (extended) | 76.8% | — |
| ARC-AGI-1 | — | 79.5% |
| Chess Puzzles | — | 21% |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 148.6 |

## Math

- Grok 4.7: 41.1 (#73)
- Inkling: 31.2 (#198)

| Benchmark | Grok 4.7 | Inkling |
|---|---|---|
| ProofBench | 34% | 0% |
| LMArena Math | 1393 | 1482 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |

## Knowledge

- Grok 4.7: 38.7 (#130)
- Inkling: 55.2 (#44)

| Benchmark | Grok 4.7 | Inkling |
|---|---|---|
| LMArena Expert | 1413 | 1468 |
| GPQA Diamond | — | 88.3% |
| SimpleQA Verified | — | 40.3% |

## Multimodal

- Grok 4.7: 28.8 (#107)
- Inkling: —

| Benchmark | Grok 4.7 | Inkling |
|---|---|---|
| Furniture Assembly | 20.8% | — |

## Multilingual

- Grok 4.7: 51.2 (#108)
- Inkling: 54.2 (#49)

| Benchmark | Grok 4.7 | Inkling |
|---|---|---|
| LMArena Non-English | 1392 | 1434 |
| LMArena Chinese | 1476 | 1495 |
| LMArena Russian | 1396 | 1430 |
| LMArena French | — | 1453 |
| LMArena German | — | 1456 |
| LMArena Japanese | — | 1428 |
| LMArena Korean | — | 1401 |
| LMArena Spanish | — | 1442 |

## Instruction Following

- Grok 4.7: 74.3 (#98)
- Inkling: 75.3 (#65)

| Benchmark | Grok 4.7 | Inkling |
|---|---|---|
| LMArena Instruction Following | 1406 | 1427 |

## Long Context

- Grok 4.7: 43.2 (#97)
- Inkling: 43.9 (#79)

| Benchmark | Grok 4.7 | Inkling |
|---|---|---|
| LMArena Longer Query | 1416 | 1436 |

## Writing & Preference

- Grok 4.7: 70.1 (#23)
- Inkling: 65.5 (#48)

| Benchmark | Grok 4.7 | Inkling |
|---|---|---|
| LMArena Text | 1397 | 1443 |
| LMArena Creative Writing | 1391 | 1390 |
| EQ-Bench Creative Writing | 2007 | 1611 |
| LMArena Multi-Turn | 1389 | 1436 |
| EQ-Bench 4 | — | 1226 |

## FAQ

### Is Grok 4.7 better than Inkling?

Grok 4.7 is the stronger model overall, scoring 46.6 to 44.1 on the Noometry Index.

### Which is cheaper, Grok 4.7 or Inkling?

Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Grok 4.7 lists at $2 and $6.

### Is Grok 4.7 or Inkling better for coding?

Grok 4.7 scores higher on coding benchmarks: 55.0 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

Grok 4.7 does, with 500K tokens against 66K.

### How many benchmarks do Grok 4.7 and Inkling share?

18 benchmarks have published results for both models. Grok 4.7 has 21 scored results on Noometry and Inkling has 41.