# Grok-3 mini vs Inkling-Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 41.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-mini-vs-inkling-small
- Last updated: 2026-10-11
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Grok-3 mini scores higher in 1 category and Inkling-Small in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 13.6.
- The biggest single-benchmark swing is ARC-AGI-1: 16.5% for Grok-3 mini and 84% for Inkling-Small.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-3 mini | Inkling-Small |
|---|---|---|
| Provider | xAI | Thinking Machines Lab |
| Noometry Index | 41.2 | 46.5 |
| Rank | 141 | 63 |
| Context | — | 524K |
| Input $/M | — | $0.45 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Grok-3 mini: 40.8 (#131)
- Inkling-Small: 43.6 (#85)

| Benchmark | Grok-3 mini | Inkling-Small |
|---|---|---|
| LMArena Coding | 1379 | 1451 |
| Aider Polyglot | 49.3% | — |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| WeirdML | 42.6% | — |

## Reasoning

- Grok-3 mini: 13.6 (#334)
- Inkling-Small: 38.6 (#63)

| Benchmark | Grok-3 mini | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 0.4% | 40.1% |
| ARC-AGI-1 | 16.5% | 84% |
| LMArena Hard Prompts | 1375 | 1423 |
| Epoch Capabilities Index | 140.35 | 150.15 |
| Kagi LLM Benchmark | 61.3% | — |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| Mystery Game Puzzles | — | 6% |

## Math

- Grok-3 mini: 42.1 (#85)
- Inkling-Small: 45.1 (#77)

| Benchmark | Grok-3 mini | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 90% |
| LMArena Math | 1386 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |

## Knowledge

- Grok-3 mini: 46.4 (#81)
- Inkling-Small: 48.2 (#77)

| Benchmark | Grok-3 mini | Inkling-Small |
|---|---|---|
| GPQA Diamond | 76.3% | 88.5% |
| LMArena Expert | 1395 | 1442 |
| SimpleQA Verified | — | 19.1% |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |

## Multimodal

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

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

## Multilingual

- Grok-3 mini: 48.1 (#145)
- Inkling-Small: 51.7 (#104)

| Benchmark | Grok-3 mini | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1352 | 1402 |
| LMArena Chinese | 1387 | 1465 |
| LMArena French | 1357 | 1436 |
| LMArena German | 1349 | 1405 |
| LMArena Japanese | 1342 | 1405 |
| LMArena Korean | 1335 | 1363 |
| LMArena Russian | 1353 | 1391 |
| LMArena Spanish | 1381 | 1428 |

## Instruction Following

- Grok-3 mini: 78.5 (#9)
- Inkling-Small: 73.8 (#114)

| Benchmark | Grok-3 mini | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1357 | 1399 |
| IFEval | 95.1% | — |

## Long Context

- Grok-3 mini: 41.0 (#147)
- Inkling-Small: 42.7 (#118)

| Benchmark | Grok-3 mini | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1372 | 1401 |
| Fiction.LiveBench | 66.7% | — |

## Writing & Preference

- Grok-3 mini: 52.5 (#169)
- Inkling-Small: 59.6 (#107)

| Benchmark | Grok-3 mini | Inkling-Small |
|---|---|---|
| LMArena Text | 1370 | 1414 |
| LMArena Creative Writing | 1342 | 1331 |
| LMArena Multi-Turn | 1355 | 1418 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | — | 1491 |
| WildBench | 65.1% | — |

## FAQ

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

Inkling-Small is the stronger model overall, scoring 46.5 to 41.2 on the Noometry Index.

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

Inkling-Small scores higher on coding benchmarks: 43.6 versus 40.8 in the Noometry coding category.

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

22 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Inkling-Small has 33.