# GPT-4.5 vs Inkling-Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 37.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-5-vs-inkling-small
- Last updated: 2026-10-11
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. GPT-4.5 scores higher in 1 category and Inkling-Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 13.9.
- The biggest single-benchmark swing is ARC-AGI-1: 10.3% for GPT-4.5 and 84% for Inkling-Small.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4.5 | Inkling-Small |
|---|---|---|
| Provider | OpenAI | Thinking Machines Lab |
| Noometry Index | 37.2 | 46.5 |
| Rank | 208 | 63 |
| Context | — | 524K |
| Input $/M | — | $0.45 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-4.5: 42.2 (#109)
- Inkling-Small: 43.6 (#85)

| Benchmark | GPT-4.5 | Inkling-Small |
|---|---|---|
| LMArena Coding | 1396 | 1451 |
| Aider Polyglot | 44.9% | — |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |

## Agentic & Tool Use

- GPT-4.5: 27.9 (#97)
- Inkling-Small: —

| Benchmark | GPT-4.5 | Inkling-Small |
|---|---|---|
| Cybench | 17.5% | — |

## Reasoning

- GPT-4.5: 13.9 (#330)
- Inkling-Small: 38.6 (#63)

| Benchmark | GPT-4.5 | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 0.8% | 40.1% |
| ARC-AGI-1 | 10.3% | 84% |
| LMArena Hard Prompts | 1403 | 1423 |
| Epoch Capabilities Index | 136.74 | 150.15 |
| SimpleBench | 34.5% | — |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| Mystery Game Puzzles | — | 6% |
| LiveBench Data Analysis | 64.3% | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |

## Math

- GPT-4.5: 32.6 (#211)
- Inkling-Small: 45.1 (#77)

| Benchmark | GPT-4.5 | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 90% |
| LMArena Math | 1412 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |

## Knowledge

- GPT-4.5: 32.5 (#211)
- Inkling-Small: 48.2 (#77)

| Benchmark | GPT-4.5 | Inkling-Small |
|---|---|---|
| GPQA Diamond | 68.7% | 88.5% |
| LMArena Expert | 1394 | 1442 |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | — | 19.1% |
| Confabulations | 13.6% | — |

## Multimodal

- GPT-4.5: 37.6 (#71)
- Inkling-Small: 39.1 (#62)

| Benchmark | GPT-4.5 | Inkling-Small |
|---|---|---|
| LMArena Vision | 1195 | 1235 |
| VPCT | 45% | — |

## Multilingual

- GPT-4.5: 52.5 (#83)
- Inkling-Small: 51.7 (#104)

| Benchmark | GPT-4.5 | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1413 | 1402 |
| LMArena Chinese | 1421 | 1465 |
| LMArena French | 1418 | 1436 |
| LMArena German | 1457 | 1405 |
| LMArena Japanese | 1416 | 1405 |
| LMArena Korean | 1392 | 1363 |
| LMArena Russian | 1419 | 1391 |
| LMArena Spanish | — | 1428 |

## Instruction Following

- GPT-4.5: 72.6 (#134)
- Inkling-Small: 73.8 (#114)

| Benchmark | GPT-4.5 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1404 | 1399 |
| LiveBench Instruction Following | 72.3% | — |

## Long Context

- GPT-4.5: 40.4 (#155)
- Inkling-Small: 42.7 (#118)

| Benchmark | GPT-4.5 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1406 | 1401 |
| Fiction.LiveBench | 63.9% | — |

## Writing & Preference

- GPT-4.5: 56.9 (#134)
- Inkling-Small: 59.6 (#107)

| Benchmark | GPT-4.5 | Inkling-Small |
|---|---|---|
| LMArena Text | 1417 | 1414 |
| LMArena Creative Writing | 1394 | 1331 |
| EQ-Bench Creative Writing | 1258 | 1491 |
| LMArena Multi-Turn | 1444 | 1418 |
| Short-Story Creative Writing | 75.6% | — |
| LiveBench Language | 61.5% | — |

## FAQ

### Is GPT-4.5 better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 37.2 on the Noometry Index.

### Is GPT-4.5 or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 42.2 in the Noometry coding category.

### How many benchmarks do GPT-4.5 and Inkling-Small share?

23 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Inkling-Small has 33.