# GPT-5.5 Instant vs Inkling-Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 42.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-5-instant-vs-inkling-small
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. GPT-5.5 Instant scores higher in 7 categories and Inkling-Small in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Inkling-Small leads 44.9 to 26.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 68.1% for GPT-5.5 Instant and 90% for Inkling-Small.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.5 Instant | Inkling-Small |
|---|---|---|
| Provider | OpenAI | Thinking Machines Lab |
| Noometry Index | 42.5 | 46.5 |
| Rank | 99 | 57 |
| Context | — | 524K |
| Input $/M | — | $0.45 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.5 Instant: 43.7 (#73)
- Inkling-Small: 43.3 (#80)

| Benchmark | GPT-5.5 Instant | Inkling-Small |
|---|---|---|
| SciCode | 48.6% | 48.7% |
| LMArena Coding | 1433 | 1451 |
| LMArena WebDev | — | 1408 |

## Reasoning

- GPT-5.5 Instant: 24.2 (#149)
- Inkling-Small: 39.0 (#53)

| Benchmark | GPT-5.5 Instant | Inkling-Small |
|---|---|---|
| CritPt | 0% | 8.3% |
| Chess Puzzles | 12% | 18% |
| LMArena Hard Prompts | 1426 | 1424 |
| Epoch Capabilities Index | 142.48 | 150.13 |
| ARC-AGI-2 | — | 40.1% |
| ARC-AGI-1 | — | 84% |
| Mystery Game Puzzles | — | 6% |

## Math

- GPT-5.5 Instant: 26.1 (#241)
- Inkling-Small: 44.9 (#65)

| Benchmark | GPT-5.5 Instant | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 26.3% | 46.3% |
| FrontierMath Tier 4 | 2.4% | 17.1% |
| OTIS Mock AIME 2024-2025 | 68.1% | 90% |
| LMArena Math | 1420 | 1453 |
| ProofBench | — | 6% |

## Knowledge

- GPT-5.5 Instant: 48.9 (#68)
- Inkling-Small: 48.3 (#71)

| Benchmark | GPT-5.5 Instant | Inkling-Small |
|---|---|---|
| GPQA Diamond | 82.5% | 88.5% |
| LMArena Expert | 1409 | 1442 |
| SimpleQA Verified | — | 19.1% |

## Multimodal

- GPT-5.5 Instant: 39.3 (#48)
- Inkling-Small: 38.4 (#59)

| Benchmark | GPT-5.5 Instant | Inkling-Small |
|---|---|---|
| LMArena Vision | 1250 | 1235 |
| LMArena Document | 1403 | — |

## Multilingual

- GPT-5.5 Instant: 53.0 (#76)
- Inkling-Small: 51.7 (#102)

| Benchmark | GPT-5.5 Instant | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1417 | 1400 |
| LMArena Chinese | 1457 | 1458 |
| LMArena French | 1428 | 1438 |
| LMArena German | 1410 | 1412 |
| LMArena Japanese | 1408 | 1399 |
| LMArena Korean | 1393 | 1355 |
| LMArena Russian | 1430 | 1392 |
| LMArena Spanish | 1430 | 1426 |

## Instruction Following

- GPT-5.5 Instant: 74.4 (#94)
- Inkling-Small: 73.9 (#112)

| Benchmark | GPT-5.5 Instant | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1407 | 1397 |

## Long Context

- GPT-5.5 Instant: 43.4 (#92)
- Inkling-Small: 42.7 (#113)

| Benchmark | GPT-5.5 Instant | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1422 | 1401 |

## Writing & Preference

- GPT-5.5 Instant: 62.0 (#81)
- Inkling-Small: 59.8 (#102)

| Benchmark | GPT-5.5 Instant | Inkling-Small |
|---|---|---|
| LMArena Text | 1419 | 1413 |
| LMArena Creative Writing | 1420 | 1330 |
| LMArena Multi-Turn | 1434 | 1420 |
| EQ-Bench Creative Writing | — | 1491 |

## FAQ

### Is GPT-5.5 Instant better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 42.5 on the Noometry Index.

### Is GPT-5.5 Instant or Inkling-Small better for coding?

They score almost the same on coding (43.7 vs 43.3); test both on your own repository before choosing.

### How many benchmarks do GPT-5.5 Instant and Inkling-Small share?

26 benchmarks have published results for both models. GPT-5.5 Instant has 27 scored results on Noometry and Inkling-Small has 33.