# Grok 3 vs Inkling-Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 39.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-vs-inkling-small
- Last updated: 2026-10-11
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Grok 3 scores higher in 2 categories and Inkling-Small in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 13.7.
- The biggest single-benchmark swing is ARC-AGI-1: 5.5% for Grok 3 and 84% for Inkling-Small.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 3 | Inkling-Small |
|---|---|---|
| Provider | xAI | Thinking Machines Lab |
| Noometry Index | 39.9 | 46.5 |
| Rank | 157 | 63 |
| Context | — | 524K |
| Input $/M | — | $0.45 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Grok 3: 41.9 (#115)
- Inkling-Small: 43.6 (#85)

| Benchmark | Grok 3 | Inkling-Small |
|---|---|---|
| LMArena Coding | 1432 | 1451 |
| Aider Polyglot | 53.3% | — |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| WeirdML | 37.2% | — |

## Agentic & Tool Use

- Grok 3: 30.5 (#76)
- Inkling-Small: —

| Benchmark | Grok 3 | Inkling-Small |
|---|---|---|
| BALROG | 29.5% | — |

## Reasoning

- Grok 3: 13.7 (#333)
- Inkling-Small: 38.6 (#63)

| Benchmark | Grok 3 | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 0% | 40.1% |
| ARC-AGI-1 | 5.5% | 84% |
| LMArena Hard Prompts | 1434 | 1423 |
| Epoch Capabilities Index | 138.33 | 150.15 |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| Mystery Game Puzzles | — | 6% |

## Math

- Grok 3: 38.0 (#145)
- Inkling-Small: 45.1 (#77)

| Benchmark | Grok 3 | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | 90% |
| LMArena Math | 1391 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| Omni-MATH | 46.4% | — |
| MATH Level 5 | 88.7% | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Grok 3: 46.2 (#82)
- Inkling-Small: 48.2 (#77)

| Benchmark | Grok 3 | Inkling-Small |
|---|---|---|
| GPQA Diamond | 75.8% | 88.5% |
| LMArena Expert | 1421 | 1442 |
| SimpleQA Verified | — | 19.1% |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |

## Multimodal

- Grok 3: —
- Inkling-Small: 39.1 (#62)

| Benchmark | Grok 3 | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |

## Multilingual

- Grok 3: 52.3 (#87)
- Inkling-Small: 51.7 (#104)

| Benchmark | Grok 3 | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1410 | 1402 |
| LMArena Chinese | 1448 | 1465 |
| LMArena French | 1460 | 1436 |
| LMArena German | 1431 | 1405 |
| LMArena Japanese | 1387 | 1405 |
| LMArena Korean | 1373 | 1363 |
| LMArena Russian | 1416 | 1391 |
| LMArena Spanish | 1417 | 1428 |

## Instruction Following

- Grok 3: 75.0 (#73)
- Inkling-Small: 73.8 (#114)

| Benchmark | Grok 3 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1409 | 1399 |
| IFEval | 88.4% | — |

## Long Context

- Grok 3: 38.7 (#192)
- Inkling-Small: 42.7 (#118)

| Benchmark | Grok 3 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1439 | 1401 |
| Fiction.LiveBench | 58.3% | — |

## Writing & Preference

- Grok 3: 55.8 (#141)
- Inkling-Small: 59.6 (#107)

| Benchmark | Grok 3 | Inkling-Small |
|---|---|---|
| LMArena Text | 1426 | 1414 |
| LMArena Creative Writing | 1414 | 1331 |
| EQ-Bench Creative Writing | 1186 | 1491 |
| LMArena Multi-Turn | 1425 | 1418 |
| Short-Story Creative Writing | 76.4% | — |
| WildBench | 84.9% | — |

## FAQ

### Is Grok 3 better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 39.9 on the Noometry Index.

### Is Grok 3 or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 41.9 in the Noometry coding category.

### How many benchmarks do Grok 3 and Inkling-Small share?

23 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Inkling-Small has 33.