# Granite 4.0 Micro vs Inkling-Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 28.8 on the Noometry Index. Granite 4.0 Micro costs 16× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/granite-4-0-micro-vs-inkling-small
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. Granite 4.0 Micro scores higher in 0 categories and Inkling-Small in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling-Small leads 48.3 to 9.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.8% for Granite 4.0 Micro and 90% for Inkling-Small.
- Granite 4.0 Micro is cheaper at $0.017 / $0.11 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 131K.

## Snapshot

| | Granite 4.0 Micro | Inkling-Small |
|---|---|---|
| Provider | IBM | Thinking Machines Lab |
| Noometry Index | 28.8 | 46.5 |
| Rank | 312 | 57 |
| Context | 131K | 524K |
| Input $/M | $0.017 | $0.45 |
| Output $/M | $0.11 | $1.20 |
| Weights | Open | Open |

## Coding

- Granite 4.0 Micro: —
- Inkling-Small: 43.3 (#80)

| Benchmark | Granite 4.0 Micro | Inkling-Small |
|---|---|---|
| LMArena WebDev | — | 1408 |
| SciCode | — | 48.7% |
| LMArena Coding | — | 1451 |

## Reasoning

- Granite 4.0 Micro: 18.5 (#261)
- Inkling-Small: 39.0 (#53)

| Benchmark | Granite 4.0 Micro | Inkling-Small |
|---|---|---|
| Chess Puzzles | 0% | 18% |
| ARC-AGI-2 | — | 40.1% |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| LMArena Hard Prompts | — | 1424 |
| Mystery Game Puzzles | — | 6% |
| Epoch Capabilities Index | — | 150.13 |

## Math

- Granite 4.0 Micro: 11.2 (#301)
- Inkling-Small: 44.9 (#65)

| Benchmark | Granite 4.0 Micro | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.8% | 90% |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| Omni-MATH | 20.9% | — |
| LMArena Math | — | 1453 |

## Knowledge

- Granite 4.0 Micro: 9.9 (#299)
- Inkling-Small: 48.3 (#71)

| Benchmark | Granite 4.0 Micro | Inkling-Small |
|---|---|---|
| GPQA Diamond | 28.3% | 88.5% |
| SimpleQA Verified | — | 19.1% |
| MMLU-Pro | 39.5% | — |
| GPQA (HELM) | 30.7% | — |
| LMArena Expert | — | 1442 |

## Multimodal

- Granite 4.0 Micro: —
- Inkling-Small: 38.4 (#59)

| Benchmark | Granite 4.0 Micro | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |

## Multilingual

- Granite 4.0 Micro: —
- Inkling-Small: 51.7 (#102)

| Benchmark | Granite 4.0 Micro | Inkling-Small |
|---|---|---|
| LMArena Non-English | — | 1400 |
| LMArena Chinese | — | 1458 |
| LMArena French | — | 1438 |
| LMArena German | — | 1412 |
| LMArena Japanese | — | 1399 |
| LMArena Korean | — | 1355 |
| LMArena Russian | — | 1392 |
| LMArena Spanish | — | 1426 |

## Instruction Following

- Granite 4.0 Micro: 70.0 (#164)
- Inkling-Small: 73.9 (#112)

| Benchmark | Granite 4.0 Micro | Inkling-Small |
|---|---|---|
| IFEval | 84.9% | — |
| LMArena Instruction Following | — | 1397 |

## Long Context

- Granite 4.0 Micro: —
- Inkling-Small: 42.7 (#113)

| Benchmark | Granite 4.0 Micro | Inkling-Small |
|---|---|---|
| LMArena Longer Query | — | 1401 |

## Writing & Preference

- Granite 4.0 Micro: 46.7 (#212)
- Inkling-Small: 59.8 (#102)

| Benchmark | Granite 4.0 Micro | Inkling-Small |
|---|---|---|
| LMArena Text | — | 1413 |
| LMArena Creative Writing | — | 1330 |
| EQ-Bench Creative Writing | — | 1491 |
| WildBench | 67% | — |
| LMArena Multi-Turn | — | 1420 |

## FAQ

### Is Granite 4.0 Micro better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 28.8 on the Noometry Index. Granite 4.0 Micro costs 16× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.

### Which is cheaper, Granite 4.0 Micro or Inkling-Small?

Granite 4.0 Micro is cheaper. It lists at $0.017 per million input tokens and $0.11 per million output tokens; Inkling-Small lists at $0.45 and $1.20.

### Which has the bigger context window?

Inkling-Small does, with 524K tokens against 131K.

### How many benchmarks do Granite 4.0 Micro and Inkling-Small share?

3 benchmarks have published results for both models. Granite 4.0 Micro has 8 scored results on Noometry and Inkling-Small has 33.