# GPT-5.4 nano vs Inkling-Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 41.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-4-nano-vs-inkling-small
- Last updated: 2026-10-10
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. GPT-5.4 nano scores higher in 0 categories and Inkling-Small in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 39.0 to 23.8.
- The biggest single-benchmark swing is ARC-AGI-2: 5.7% for GPT-5.4 nano and 40.1% for Inkling-Small.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 400K.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| Provider | OpenAI | Thinking Machines Lab |
| Noometry Index | 41.9 | 46.5 |
| Rank | 111 | 57 |
| Context | 400K | 524K |
| Input $/M | $0.20 | $0.45 |
| Output $/M | $1.25 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.4 nano: 43.1 (#82)
- Inkling-Small: 43.3 (#80)

| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| SciCode | 46.9% | 48.7% |
| LMArena Coding | 1404 | 1451 |
| LMArena WebDev | — | 1408 |
| WeirdML | 49.2% | — |
| ALE-Bench | 1,005 | — |

## Reasoning

- GPT-5.4 nano: 23.8 (#159)
- Inkling-Small: 39.0 (#53)

| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 5.7% | 40.1% |
| ARC-AGI-1 | 51.5% | 84% |
| CritPt | 9.3% | 8.3% |
| Chess Puzzles | 30% | 18% |
| LMArena Hard Prompts | 1380 | 1424 |
| Mystery Game Puzzles | 9% | 6% |
| Epoch Capabilities Index | 145.78 | 150.13 |
| Kagi LLM Benchmark | 39.7% | — |
| DTBench | 80.3% | — |
| LMCA | 36.9% | — |
| ForecastBench | 57.3 | — |

## Math

- GPT-5.4 nano: 40.7 (#76)
- Inkling-Small: 44.9 (#65)

| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 44.9% | 46.3% |
| FrontierMath Tier 4 | 12.2% | 17.1% |
| OTIS Mock AIME 2024-2025 | 87.8% | 90% |
| ProofBench | 5% | 6% |
| LMArena Math | 1406 | 1453 |
| FrontierMath (Feb 2025 set) | 25.9% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |

## Knowledge

- GPT-5.4 nano: 41.8 (#94)
- Inkling-Small: 48.3 (#71)

| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| GPQA Diamond | 78.5% | 88.5% |
| SimpleQA Verified | 11.7% | 19.1% |
| LMArena Expert | 1397 | 1442 |
| Vectara Hallucination Rate | 3.1% | — |

## Multimodal

- GPT-5.4 nano: 36.0 (#73)
- Inkling-Small: 38.4 (#59)

| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| LMArena Vision | 1196 | 1235 |

## Multilingual

- GPT-5.4 nano: 48.8 (#136)
- Inkling-Small: 51.7 (#102)

| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1359 | 1400 |
| LMArena Chinese | 1391 | 1458 |
| LMArena French | 1396 | 1438 |
| LMArena German | 1368 | 1412 |
| LMArena Japanese | 1342 | 1399 |
| LMArena Korean | 1321 | 1355 |
| LMArena Russian | 1363 | 1392 |
| LMArena Spanish | 1368 | 1426 |

## Instruction Following

- GPT-5.4 nano: 72.1 (#139)
- Inkling-Small: 73.9 (#112)

| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1362 | 1397 |

## Long Context

- GPT-5.4 nano: 41.6 (#131)
- Inkling-Small: 42.7 (#113)

| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1365 | 1401 |

## Writing & Preference

- GPT-5.4 nano: 55.9 (#137)
- Inkling-Small: 59.8 (#102)

| Benchmark | GPT-5.4 nano | Inkling-Small |
|---|---|---|
| LMArena Text | 1372 | 1413 |
| LMArena Creative Writing | 1313 | 1330 |
| LMArena Multi-Turn | 1382 | 1420 |
| EQ-Bench Creative Writing | — | 1491 |

## FAQ

### Is GPT-5.4 nano better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 41.9 on the Noometry Index.

### Which is cheaper, GPT-5.4 nano or Inkling-Small?

GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; Inkling-Small lists at $0.45 and $1.20.

### Is GPT-5.4 nano or Inkling-Small better for coding?

They score almost the same on coding (43.1 vs 43.3); test both on your own repository before choosing.

### Which has the bigger context window?

Inkling-Small does, with 524K tokens against 400K.

### How many benchmarks do GPT-5.4 nano and Inkling-Small share?

31 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Inkling-Small has 33.