# Claude 3 Sonnet vs Inkling-Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 29.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-inkling-small
- Last updated: 2026-10-11
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Inkling-Small in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Inkling-Small leads 45.1 to 10.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 90% for Inkling-Small.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Sonnet | Inkling-Small |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 29.0 | 46.5 |
| Rank | 319 | 63 |
| Context | — | 524K |
| Input $/M | — | $0.45 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Sonnet: 29.6 (#302)
- Inkling-Small: 43.6 (#85)

| Benchmark | Claude 3 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Coding | 1223 | 1451 |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Reasoning

- Claude 3 Sonnet: 20.5 (#237)
- Inkling-Small: 38.6 (#63)

| Benchmark | Claude 3 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1423 |
| Epoch Capabilities Index | 120.7 | 150.15 |
| ARC-AGI-2 | — | 40.1% |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| Mystery Game Puzzles | — | 6% |
| DTBench | 53.6% | — |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.7 (#310)
- Inkling-Small: 45.1 (#77)

| Benchmark | Claude 3 Sonnet | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 90% |
| LMArena Math | 1213 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| MATH Level 5 | 18.2% | — |

## Knowledge

- Claude 3 Sonnet: 21.1 (#276)
- Inkling-Small: 48.2 (#77)

| Benchmark | Claude 3 Sonnet | Inkling-Small |
|---|---|---|
| GPQA Diamond | 40.6% | 88.5% |
| LMArena Expert | 1173 | 1442 |
| SimpleQA Verified | — | 19.1% |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 25.2 (#125)
- Inkling-Small: 39.1 (#62)

| Benchmark | Claude 3 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Vision | 984 | 1235 |

## Multilingual

- Claude 3 Sonnet: 37.8 (#234)
- Inkling-Small: 51.7 (#104)

| Benchmark | Claude 3 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1205 | 1402 |
| LMArena Chinese | 1189 | 1465 |
| LMArena French | 1229 | 1436 |
| LMArena German | 1204 | 1405 |
| LMArena Japanese | 1131 | 1405 |
| LMArena Korean | 1128 | 1363 |
| LMArena Russian | 1227 | 1391 |
| LMArena Spanish | 1204 | 1428 |

## Instruction Following

- Claude 3 Sonnet: 62.8 (#235)
- Inkling-Small: 73.8 (#114)

| Benchmark | Claude 3 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1199 | 1399 |

## Long Context

- Claude 3 Sonnet: 36.7 (#228)
- Inkling-Small: 42.7 (#118)

| Benchmark | Claude 3 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1211 | 1401 |

## Writing & Preference

- Claude 3 Sonnet: 42.1 (#238)
- Inkling-Small: 59.6 (#107)

| Benchmark | Claude 3 Sonnet | Inkling-Small |
|---|---|---|
| LMArena Text | 1218 | 1414 |
| LMArena Creative Writing | 1186 | 1331 |
| LMArena Multi-Turn | 1227 | 1418 |
| EQ-Bench Creative Writing | — | 1491 |

## FAQ

### Is Claude 3 Sonnet better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 29.0 on the Noometry Index.

### Is Claude 3 Sonnet or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 29.6 in the Noometry coding category.

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

21 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Inkling-Small has 33.
