Inkling Small (free)
Thinking Machines · released Jul 30, 2026
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...
Specification
- Context window
- 1.05M
- Max output
- 262K
- Knowledge cutoff
- Not stated
- Parameters
- 266B
- Licence
- apache-2.0
- Serving providers
- 1
- Moderated
- No
- Uptime
- 100.0%
Intelligence
25.7
77th percentile
Coding
52.9
Coding Index
Agentic
23.5
Agentic Index
Output speed
93 t/s
Median across providers
Latency
1.43s
Time to first token
Cost per task
Free
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- GPQA Diamond89.5%
- AA-LCR (long context)75.7%
- SciCode49.7%
- Humanity's Last Exam33.3%
- τ²-bench (Telecom)18.8%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| GPQA Diamond | 89.5% |
| AA-LCR (long context) | 75.7% |
| SciCode | 49.7% |
| Humanity's Last Exam | 33.3% |
| τ²-bench (Telecom) | 18.8% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- GLM 5.1Z.ai26.1
- MiMo-V2.5-ProXiaomi26.0
- Claude Opus 4Anthropic26.0
- Kimi K2.7 CodeMoonshot AI25.8
- Inkling Small (free)Thinking Machines25.7
- Inkling SmallThinking Machines25.7
- Grok 4.20xAI25.7
- Hy3Tencent25.3
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| GLM 5.1 | 26.1 |
| MiMo-V2.5-Pro | 26.0 |
| Claude Opus 4 | 26.0 |
| Kimi K2.7 Code | 25.8 |
| Inkling Small (free) | 25.7 |
| Inkling Small | 25.7 |
| Grok 4.20 | 25.7 |
| Hy3 | 25.3 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- Free
- Output / 1M tokens
- Free
- Cached input / 1M
- Not offered
- Blended 3:1
- Free
One task, estimated
Free
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.