# Claude Haiku 5.5 vs Inkling-Small

> Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 46.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-haiku-5-5-vs-inkling-small
- Last updated: 2026-10-12
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. Claude Haiku 5.5 scores higher in 4 categories and Inkling-Small in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 5.5 leads 73.6 to 45.1.
- The biggest single-benchmark swing is FrontierMath Tier 4: 46.3% for Claude Haiku 5.5 and 17.1% for Inkling-Small.
- Claude Haiku 5.5 is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Claude Haiku 5.5 accepts more context: 1M tokens versus 524K.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Haiku 5.5 | Inkling-Small |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 49.5 | 46.5 |
| Rank | 52 | 63 |
| Context | 1M | 524K |
| Input $/M | $0.10 | $0.45 |
| Output $/M | $0.50 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Claude Haiku 5.5: 49.2 (#50)
- Inkling-Small: 43.6 (#85)

| Benchmark | Claude Haiku 5.5 | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1587 | 1409 |
| SciCode | — | 48.7% |
| LMArena Coding | — | 1451 |

## Reasoning

- Claude Haiku 5.5: 35.2 (#69)
- Inkling-Small: 38.6 (#63)

| Benchmark | Claude Haiku 5.5 | Inkling-Small |
|---|---|---|
| Mystery Game Puzzles | 30% | 6% |
| ARC-AGI-2 | — | 40.1% |
| NYT Connections (extended) | 65.7% | — |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| LMArena Hard Prompts | — | 1423 |
| Epoch Capabilities Index | — | 150.15 |

## Math

- Claude Haiku 5.5: 73.6 (#18)
- Inkling-Small: 45.1 (#77)

| Benchmark | Claude Haiku 5.5 | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 75.1% | 46.3% |
| FrontierMath Tier 4 | 46.3% | 17.1% |
| OTIS Mock AIME 2024-2025 | 98.9% | 90% |
| ProofBench | — | 6% |
| LMArena Math | — | 1459 |

## Knowledge

- Claude Haiku 5.5: 50.8 (#70)
- Inkling-Small: 48.2 (#77)

| Benchmark | Claude Haiku 5.5 | Inkling-Small |
|---|---|---|
| GPQA Diamond | 89.6% | 88.5% |
| SimpleQA Verified | 23.8% | 19.1% |
| LMArena Expert | — | 1442 |

## Multimodal

- Claude Haiku 5.5: 43.7 (#21)
- Inkling-Small: 39.1 (#62)

| Benchmark | Claude Haiku 5.5 | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |
| Furniture Assembly | 47.5% | — |

## Multilingual

- Claude Haiku 5.5: —
- Inkling-Small: 51.7 (#104)

| Benchmark | Claude Haiku 5.5 | Inkling-Small |
|---|---|---|
| LMArena Non-English | — | 1402 |
| LMArena Chinese | — | 1465 |
| LMArena French | — | 1436 |
| LMArena German | — | 1405 |
| LMArena Japanese | — | 1405 |
| LMArena Korean | — | 1363 |
| LMArena Russian | — | 1391 |
| LMArena Spanish | — | 1428 |

## Instruction Following

- Claude Haiku 5.5: —
- Inkling-Small: 73.8 (#114)

| Benchmark | Claude Haiku 5.5 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | — | 1399 |

## Long Context

- Claude Haiku 5.5: —
- Inkling-Small: 42.7 (#118)

| Benchmark | Claude Haiku 5.5 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | — | 1401 |

## Writing & Preference

- Claude Haiku 5.5: —
- Inkling-Small: 59.6 (#107)

| Benchmark | Claude Haiku 5.5 | Inkling-Small |
|---|---|---|
| LMArena Text | — | 1414 |
| LMArena Creative Writing | — | 1331 |
| EQ-Bench Creative Writing | — | 1491 |
| LMArena Multi-Turn | — | 1418 |

## FAQ

### Is Claude Haiku 5.5 better than Inkling-Small?

Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 46.5 on the Noometry Index.

### Which is cheaper, Claude Haiku 5.5 or Inkling-Small?

Claude Haiku 5.5 is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Inkling-Small lists at $0.45 and $1.20.

### Is Claude Haiku 5.5 or Inkling-Small better for coding?

Claude Haiku 5.5 scores higher on coding benchmarks: 49.2 versus 43.6 in the Noometry coding category.

### Which has the bigger context window?

Claude Haiku 5.5 does, with 1M tokens against 524K.

### How many benchmarks do Claude Haiku 5.5 and Inkling-Small share?

7 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and Inkling-Small has 33.