Approved models
3
Records published from this collection
Provider information
lab
Review approach
Verify each model’s source, terms, capabilities, and current availability
Essential AI develops the Rnj family of open-weight models. The two Rnj-1 entries serve different purposes: the base checkpoint is a starting point for further training, while the instruction-tuned checkpoint is intended for interactive coding, STEM questions and tool-driven workflows.
Choose Rnj-1 Instruct when evaluating an assistant. Choose Rnj-1 Base when you need a training foundation. A base model should not be judged by pasting a chat prompt into a wrapper designed for an instruction-tuned model.
Read the model card alongside the exact checkpoint configuration. Context extensions, quantization and serving engines can change the behavior you measure. Keep model weights, tokenizer, chat template and runtime versions together in your test record.
For coding, a useful evaluation is a small collection of real issues with executable tests. Count regressions, incomplete fixes and unnecessary changes as well as successful patches. For factual answers, retain a retrieval or verification step instead of treating fluent output as evidence.
Browse the model directory to compare open-weight alternatives and hosted routes.
Review each record individually; collection membership does not imply a recommendation or guarantee of availability.
| Rnj-1 Base Essential AI | 13.5 | 32.77K | — | — | — |
| Rnj-1 Instruct Essential AI | 23.5 | 32.77K | — | — | — |
| Rnj-1.5 Instruct Essential AI | 17.8 | 160K | — | — | — |
1–3 of 3 models · select a column to sort
About this order: Recommended shows our editorial shortlist first, followed by recent releases. The spec score is a 0–100 figure SyncDev calculates from each vendor's published specifications — context window, reasoning support, input modalities, tool calling, maximum output and how recently the model shipped. It measures breadth of capability, not benchmark performance, so a higher-scoring model is not automatically the better choice for your task.