# GPT-5.3 Chat vs Inkling-Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 42.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-3-chat-vs-inkling-small
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GPT-5.3 Chat scores higher in 1 category and Inkling-Small in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 28.5.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Chat.
- Inkling-Small accepts more context: 524K tokens versus 128K.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.3 Chat | Inkling-Small |
|---|---|---|
| Provider | OpenAI | Thinking Machines Lab |
| Noometry Index | 42.8 | 46.5 |
| Rank | 109 | 63 |
| Context | 128K | 524K |
| Input $/M | $1.75 | $0.45 |
| Output $/M | $14 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.3 Chat: 41.4 (#124)
- Inkling-Small: 43.6 (#85)

| Benchmark | GPT-5.3 Chat | Inkling-Small |
|---|---|---|
| LMArena Coding | 1408 | 1451 |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |

## Reasoning

- GPT-5.3 Chat: 28.5 (#102)
- Inkling-Small: 38.6 (#63)

| Benchmark | GPT-5.3 Chat | Inkling-Small |
|---|---|---|
| LMArena Hard Prompts | 1399 | 1423 |
| ARC-AGI-2 | — | 40.1% |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| Mystery Game Puzzles | — | 6% |
| Epoch Capabilities Index | — | 150.15 |

## Math

- GPT-5.3 Chat: 38.2 (#142)
- Inkling-Small: 45.1 (#77)

| Benchmark | GPT-5.3 Chat | Inkling-Small |
|---|---|---|
| LMArena Math | 1389 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 90% |
| ProofBench | — | 6% |

## Knowledge

- GPT-5.3 Chat: 38.8 (#140)
- Inkling-Small: 48.2 (#77)

| Benchmark | GPT-5.3 Chat | Inkling-Small |
|---|---|---|
| LMArena Expert | 1397 | 1442 |
| GPQA Diamond | — | 88.5% |
| SimpleQA Verified | — | 19.1% |

## Multimodal

- GPT-5.3 Chat: —
- Inkling-Small: 39.1 (#62)

| Benchmark | GPT-5.3 Chat | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |

## Multilingual

- GPT-5.3 Chat: 50.3 (#124)
- Inkling-Small: 51.7 (#104)

| Benchmark | GPT-5.3 Chat | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1382 | 1402 |
| LMArena Chinese | 1432 | 1465 |
| LMArena French | 1397 | 1436 |
| LMArena German | 1384 | 1405 |
| LMArena Japanese | 1352 | 1405 |
| LMArena Korean | 1346 | 1363 |
| LMArena Russian | 1400 | 1391 |
| LMArena Spanish | 1371 | 1428 |

## Instruction Following

- GPT-5.3 Chat: 72.8 (#129)
- Inkling-Small: 73.8 (#114)

| Benchmark | GPT-5.3 Chat | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1378 | 1399 |

## Long Context

- GPT-5.3 Chat: 42.6 (#120)
- Inkling-Small: 42.7 (#118)

| Benchmark | GPT-5.3 Chat | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1396 | 1401 |

## Writing & Preference

- GPT-5.3 Chat: 63.1 (#68)
- Inkling-Small: 59.6 (#107)

| Benchmark | GPT-5.3 Chat | Inkling-Small |
|---|---|---|
| LMArena Text | 1389 | 1414 |
| LMArena Creative Writing | 1355 | 1331 |
| EQ-Bench Creative Writing | 1690 | 1491 |
| LMArena Multi-Turn | 1412 | 1418 |

## FAQ

### Is GPT-5.3 Chat better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 42.8 on the Noometry Index.

### Which is cheaper, GPT-5.3 Chat or Inkling-Small?

Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; GPT-5.3 Chat lists at $1.75 and $14.

### Is GPT-5.3 Chat or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 41.4 in the Noometry coding category.

### Which has the bigger context window?

Inkling-Small does, with 524K tokens against 128K.

### How many benchmarks do GPT-5.3 Chat and Inkling-Small share?

18 benchmarks have published results for both models. GPT-5.3 Chat has 18 scored results on Noometry and Inkling-Small has 33.