thinkingmachines
Comparing 2 models from thinkingmachines.
| Model | Total ▼ | Released | Context | CoT | Tooling | Creative Writing | Language | Utility | Reasoning | Text Editing | Rule Following | Hallucination |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Thinking Machines Inkling (Reasoning) | 90.78% | Jul 18, 26 | 1m | – | 100.00% | 80.19% | 95.61% | 93.19% | 86.03% | 98.23% | 76.65% | 96.34% |
| Thinking Machines Inkling | 73.96% | Jul 18, 26 | 1m | – | 56.68% | 80.27% | 76.49% | 65.97% | 64.85% | 93.22% | 61.48% | 92.70% |
Model Performance
Cost vs Performance
Compares total benchmark cost against overall score for thinkingmachines models. Quadrant lines are drawn at the median values.
Cost Breakdown
Total benchmark cost per model, broken down by input, reasoning, and output tokens. Toggle between USD and token views.