Loading comparison…
HEAD TO HEAD
Nokia: anyjev and ORG2 AI: wald, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | nokia/anyjev | org2ai/wald |
|---|---|---|
| Summary | A training-free layer that turns an open LLM into a decision model. It reads typed choice, yes/no and score answers from one prefill, removes option-order bias with no labels and, from a few hundred labels, calibrates or fits a closed-form head. Weights stay untouched. | A 4B decision model fine-tuned from Qwen3.5-4B-Base. A state and typed questions (choice, yes/no, score) go in; a temperature-calibrated probability for every option comes out of one pass, through a self-hosted /v1/systemone-compatible server. Apache-2.0 weights and code. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify, route |
| Architecture | anyjev | wald |
| Fine-tuned from | qwen/qwen3-8b | qwen/qwen3.5-4b-base |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 77.1% | 88.3% |
| Calibration error | 0.034 | 0.045 |
| Valid action rate | — | — |
| Median latency | — | 33 ms |
| p95 latency | — | 168 ms |
| Evaluation suite | LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question | JevBench public set (231 items; 204 correct), maker's run with the JevBench CLI, v1.2, effort none; items used as a development scoreboard |
| Latest version | 0.2.0 | 1.2.0 |
| Variants | — | Dockerfile, LICENSE, NOTICE, model-files, reference, server |
| Size of latest version | — | 7.9 GB |
| Files | 0 | 38 |
| Downloads | 0 | 1 |
| Stars | 1 | 0 |
| Tags | system-one, qwen, training-free, calibrated, vllm, 8b | system-one, qwen, calibrated, gguf, vllm, jevbench, 4.2b |
| Updated | Oct 25, 2026 | Nov 9, 2026 |
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
anyjev is from Nokia and wald from ORG2 AI. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. wald is the smaller model, at 4.2B parameters to 8.0B.
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, wald 88.3% on JevBench public set (231 items; 204 correct), maker's run with the JevBench CLI, v1.2, effort none; items used as a development scoreboard — so the numbers do not rank them. Test both on your own labelled examples.
anyjev: Free (open weights). wald: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull nokia/anyjev and systemone pull org2ai/wald download the weights.