Quality
#24/7641.2
Overall quality score
🇺🇸Thinking MachinesOpen sourceThinking Machines: Inkling Small.
See how Thinking Machines: Inkling Small compares with other broadly useful AI models across quality, speed, price, context, and practical capabilities.
Speed
#9/76146 t/s
Output tokens per second
Input price
#38/76$0.45/1M
Per 1M tokens
Output price
#32/76$1.20/1M
Per 1M tokens
Context
#34/76524.3K
Content read at once
Comparison summary
Thinking Machines: Inkling Small ranks #24 of 76 for overall quality and #9 for response speed in the current catalogue.
Its listed input price is $0.45/1M, output price is $1.20/1M, and it can work with up to 524.3K of context at once.
Its strongest areas in the current data are coding, everyday help, math and logic.
Practical specifications
- Company
- Thinking Machines
- Reasoning
- Yes
- Open weights
- Yes
- Input
- Text, Image, Audio
- Output
- Text
- Context window
- 524.3K
Thinking Machines: Inkling Small technical benchmarks.
Named evaluation records for technical comparison. Results retain their original benchmark names and sources.
| Benchmark | Area | Inkling Small | Source |
|---|---|---|---|
| Intelligence Index | overallQuality | 41.2 | OpenRouter / artificial-analysis |
| Coding Index | coding | 52.9 | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 31.9 | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | 89.5 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 33.3 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 69.3 | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | 38.4 | OpenRouter model benchmarks |
| CritPt | CritPt | 8.3 | OpenRouter model benchmarks |
| SciCode | SciCode | 48.7 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 33.2 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 37 | OpenRouter model benchmarks |
Quality benchmarks
See where Thinking Machines: Inkling Small stands.
The darker bar marks Thinking Machines: Inkling Small; the lighter bars provide context from other leading models.
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better