# GPT-4o mini vs Inkling-Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 25.5 on the Noometry Index. GPT-4o mini costs 2.4× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-4o-mini-vs-inkling-small
- Last updated: 2026-10-11
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and Inkling-Small in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Inkling-Small leads 45.1 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.9% for GPT-4o mini and 90% for Inkling-Small.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 128K.
- Inkling-Small has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4o mini | Inkling-Small |
|---|---|---|
| Provider | OpenAI | Thinking Machines Lab |
| Noometry Index | 25.5 | 46.5 |
| Rank | 343 | 63 |
| Context | 128K | 524K |
| Input $/M | $0.15 | $0.45 |
| Output $/M | $0.60 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-4o mini: 22.0 (#335)
- Inkling-Small: 43.6 (#85)

| Benchmark | GPT-4o mini | Inkling-Small |
|---|---|---|
| LMArena Coding | 1290 | 1451 |
| Aider Polyglot | 3.6% | — |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |

## Agentic & Tool Use

- GPT-4o mini: 27.5 (#101)
- Inkling-Small: —

| Benchmark | GPT-4o mini | Inkling-Small |
|---|---|---|
| BALROG | 17.4% | — |

## Reasoning

- GPT-4o mini: 8.7 (#347)
- Inkling-Small: 38.6 (#63)

| Benchmark | GPT-4o mini | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 0% | 40.1% |
| Chess Puzzles | 0% | 18% |
| LMArena Hard Prompts | 1267 | 1423 |
| Mystery Game Puzzles | 12% | 6% |
| Epoch Capabilities Index | 126.56 | 150.15 |
| SimpleBench | 10.7% | — |
| Kagi LLM Benchmark | 28.8% | — |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| LiveBench Reasoning | 32.8% | — |
| DTBench | 54.4% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |

## Math

- GPT-4o mini: 10.4 (#314)
- Inkling-Small: 45.1 (#77)

| Benchmark | GPT-4o mini | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | 46.3% |
| OTIS Mock AIME 2024-2025 | 6.9% | 90% |
| LMArena Math | 1267 | 1459 |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| MATH Level 5 | 52.6% | — |
| GSM8K | 91.3% | — |

## Knowledge

- GPT-4o mini: 17.7 (#284)
- Inkling-Small: 48.2 (#77)

| Benchmark | GPT-4o mini | Inkling-Small |
|---|---|---|
| GPQA Diamond | 37.7% | 88.5% |
| SimpleQA Verified | 8.3% | 19.1% |
| LMArena Expert | 1235 | 1442 |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |

## Multimodal

- GPT-4o mini: 25.9 (#122)
- Inkling-Small: 39.1 (#62)

| Benchmark | GPT-4o mini | Inkling-Small |
|---|---|---|
| LMArena Vision | 1066 | 1235 |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |

## Multilingual

- GPT-4o mini: 42.0 (#199)
- Inkling-Small: 51.7 (#104)

| Benchmark | GPT-4o mini | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1266 | 1402 |
| LMArena Chinese | 1265 | 1465 |
| LMArena French | 1297 | 1436 |
| LMArena German | 1272 | 1405 |
| LMArena Japanese | 1216 | 1405 |
| LMArena Korean | 1195 | 1363 |
| LMArena Russian | 1275 | 1391 |
| LMArena Spanish | 1276 | 1428 |

## Instruction Following

- GPT-4o mini: 61.9 (#239)
- Inkling-Small: 73.8 (#114)

| Benchmark | GPT-4o mini | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1258 | 1399 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |

## Long Context

- GPT-4o mini: 39.1 (#186)
- Inkling-Small: 42.7 (#118)

| Benchmark | GPT-4o mini | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1289 | 1401 |

## Writing & Preference

- GPT-4o mini: 39.5 (#248)
- Inkling-Small: 59.6 (#107)

| Benchmark | GPT-4o mini | Inkling-Small |
|---|---|---|
| LMArena Text | 1286 | 1414 |
| LMArena Creative Writing | 1268 | 1331 |
| EQ-Bench Creative Writing | 873 | 1491 |
| LMArena Multi-Turn | 1285 | 1418 |
| Short-Story Creative Writing | 67.2% | — |
| WildBench | 79.1% | — |
| LiveBench Language | 28.6% | — |

## FAQ

### Is GPT-4o mini better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 25.5 on the Noometry Index. GPT-4o mini costs 2.4× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.

### Which is cheaper, GPT-4o mini or Inkling-Small?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Inkling-Small lists at $0.45 and $1.20.

### Is GPT-4o mini or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 22.0 in the Noometry coding category.

### Which has the bigger context window?

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

### How many benchmarks do GPT-4o mini and Inkling-Small share?

27 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Inkling-Small has 33.