# Claude 2 vs Inkling-Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 25.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-vs-inkling-small
- Last updated: 2026-10-12
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. Claude 2 scores higher in 0 categories and Inkling-Small in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Inkling-Small leads 45.1 to 9.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 2 and 90% for Inkling-Small.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 2 | Inkling-Small |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 25.0 | 46.5 |
| Rank | 346 | 63 |
| Context | — | 524K |
| Input $/M | — | $0.45 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Claude 2: —
- Inkling-Small: 43.6 (#85)

| Benchmark | Claude 2 | Inkling-Small |
|---|---|---|
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| LMArena Coding | — | 1451 |
| HumanEval+ | 61.6% | — |

## Reasoning

- Claude 2: 21.7 (#216)
- Inkling-Small: 38.6 (#63)

| Benchmark | Claude 2 | Inkling-Small |
|---|---|---|
| Epoch Capabilities Index | 120.13 | 150.15 |
| ARC-AGI-2 | — | 40.1% |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| LMArena Hard Prompts | — | 1423 |
| Mystery Game Puzzles | — | 6% |
| DTBench | 51.9% | — |

## Math

- Claude 2: 9.3 (#320)
- Inkling-Small: 45.1 (#77)

| Benchmark | Claude 2 | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 90% |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| LMArena Math | — | 1459 |
| MATH Level 5 | 11.7% | — |

## Knowledge

- Claude 2: 16.9 (#287)
- Inkling-Small: 48.2 (#77)

| Benchmark | Claude 2 | Inkling-Small |
|---|---|---|
| GPQA Diamond | 34.7% | 88.5% |
| SimpleQA Verified | — | 19.1% |
| LMArena Expert | — | 1442 |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |

## Multimodal

- Claude 2: —
- Inkling-Small: 39.1 (#62)

| Benchmark | Claude 2 | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |

## Multilingual

- Claude 2: —
- Inkling-Small: 51.7 (#104)

| Benchmark | Claude 2 | 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 2: —
- Inkling-Small: 73.8 (#114)

| Benchmark | Claude 2 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | — | 1399 |

## Long Context

- Claude 2: —
- Inkling-Small: 42.7 (#118)

| Benchmark | Claude 2 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | — | 1401 |

## Writing & Preference

- Claude 2: —
- Inkling-Small: 59.6 (#107)

| Benchmark | Claude 2 | Inkling-Small |
|---|---|---|
| LMArena Text | — | 1414 |
| LMArena Creative Writing | — | 1331 |
| EQ-Bench Creative Writing | — | 1491 |
| LMArena Multi-Turn | — | 1418 |

## FAQ

### Is Claude 2 better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 25.0 on the Noometry Index.

### How many benchmarks do Claude 2 and Inkling-Small share?

3 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Inkling-Small has 33.