# Inkling-Small vs o1-mini

> Inkling-Small is the stronger model overall, scoring 46.5 to 34.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/inkling-small-vs-o1-mini
- Last updated: 2026-10-11
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and o1-mini in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 8.8.
- The biggest single-benchmark swing is ARC-AGI-1: 84% for Inkling-Small and 14% for o1-mini.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | Inkling-Small | o1-mini |
|---|---|---|
| Provider | Thinking Machines Lab | OpenAI |
| Noometry Index | 46.5 | 34.0 |
| Rank | 63 | 235 |
| Context | 524K | — |
| Input $/M | $0.45 | — |
| Output $/M | $1.20 | — |
| Weights | Open | Proprietary |

## Coding

- Inkling-Small: 43.6 (#85)
- o1-mini: 35.5 (#224)

| Benchmark | Inkling-Small | o1-mini |
|---|---|---|
| LMArena Coding | 1451 | 1362 |
| Aider Polyglot | — | 32.9% |
| LMArena WebDev | 1409 | — |
| SciCode | 48.7% | — |
| WeirdML | — | 36.3% |
| LiveBench Coding | — | 48% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |

## Agentic & Tool Use

- Inkling-Small: —
- o1-mini: 24.6 (#118)

| Benchmark | Inkling-Small | o1-mini |
|---|---|---|
| Cybench | — | 10% |

## Reasoning

- Inkling-Small: 38.6 (#63)
- o1-mini: 8.8 (#346)

| Benchmark | Inkling-Small | o1-mini |
|---|---|---|
| ARC-AGI-2 | 40.1% | 0.8% |
| ARC-AGI-1 | 84% | 14% |
| LMArena Hard Prompts | 1423 | 1333 |
| Epoch Capabilities Index | 150.15 | 135.82 |
| SimpleBench | — | 18.1% |
| CritPt | 8.3% | — |
| Chess Puzzles | 18% | — |
| LiveBench Reasoning | — | 72.3% |
| Mystery Game Puzzles | 6% | — |
| LiveBench Data Analysis | — | 57.9% |
| LiveBench | — | 57.8% |

## Math

- Inkling-Small: 45.1 (#77)
- o1-mini: 35.4 (#186)

| Benchmark | Inkling-Small | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 90% | 46.9% |
| LMArena Math | 1459 | 1358 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |

## Knowledge

- Inkling-Small: 48.2 (#77)
- o1-mini: 34.9 (#192)

| Benchmark | Inkling-Small | o1-mini |
|---|---|---|
| GPQA Diamond | 88.5% | 62.4% |
| LMArena Expert | 1442 | 1316 |
| SimpleQA Verified | 19.1% | — |
| Confabulations | — | 18.6% |

## Multimodal

- Inkling-Small: 39.1 (#62)
- o1-mini: —

| Benchmark | Inkling-Small | o1-mini |
|---|---|---|
| LMArena Vision | 1235 | — |

## Multilingual

- Inkling-Small: 51.7 (#104)
- o1-mini: 43.6 (#182)

| Benchmark | Inkling-Small | o1-mini |
|---|---|---|
| LMArena Non-English | 1402 | 1289 |
| LMArena Chinese | 1465 | 1314 |
| LMArena French | 1436 | 1293 |
| LMArena German | 1405 | 1278 |
| LMArena Japanese | 1405 | 1245 |
| LMArena Korean | 1363 | 1223 |
| LMArena Russian | 1391 | 1283 |
| LMArena Spanish | 1428 | 1303 |

## Instruction Following

- Inkling-Small: 73.8 (#114)
- o1-mini: 66.7 (#206)

| Benchmark | Inkling-Small | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1399 | 1304 |
| LiveBench Instruction Following | — | 65.4% |

## Long Context

- Inkling-Small: 42.7 (#118)
- o1-mini: 40.1 (#161)

| Benchmark | Inkling-Small | o1-mini |
|---|---|---|
| LMArena Longer Query | 1401 | 1320 |

## Writing & Preference

- Inkling-Small: 59.6 (#107)
- o1-mini: 48.4 (#202)

| Benchmark | Inkling-Small | o1-mini |
|---|---|---|
| LMArena Text | 1414 | 1317 |
| LMArena Creative Writing | 1331 | 1244 |
| LMArena Multi-Turn | 1418 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 1491 | — |
| LiveBench Language | — | 40.9% |

## FAQ

### Is Inkling-Small better than o1-mini?

Inkling-Small is the stronger model overall, scoring 46.5 to 34.0 on the Noometry Index.

### Is Inkling-Small or o1-mini better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 35.5 in the Noometry coding category.

### How many benchmarks do Inkling-Small and o1-mini share?

22 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and o1-mini has 39.