Ultra-small English encoders (17M, 68M and 395M) fine-tuned from Ettin rerankers. Each answers choice, noul and score questions with a probability per candidate and no generated text. Experimental v0 by one developer; the weights have no licence assigned yet.
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, noul, score
choice, score, noul, classify, route
Architecture
bekko
wald
Fine-tuned from
cross-encoder/ettin-reranker-400m-v1
qwen/qwen3.5-4b-base
License
Unassigned: the weights licence is not finalised (treated as non-commercial); training code MIT
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
88.3%
Calibration error
—
0.045
Valid action rate
—
—
Median latency
5 ms
33 ms
p95 latency
5.4 ms
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.
Questions
What is the difference between bekko-system-one and wald?
bekko-system-one is from Yuichi Tateno (hotchpotch) and wald from ORG2 AI. Both have open weights you can download and run. Both answer choice, noul and score questions. Only wald answers classify and route. bekko-system-one is the smaller model, at 395M parameters to 4.2B. bekko-system-one is licensed other; wald, apache-2.0.
Which is more accurate, bekko-system-one or wald?
Only wald publishes an accuracy figure (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); bekko-system-one does not, so there is no comparison to make without your own test.
Which is cheaper, bekko-system-one or wald?
bekko-system-one: Free (open weights). wald: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, bekko-system-one or wald?
By their publishers’ figures, bekko-system-one answers in about 5 ms at the median and wald in about 33 ms — measured on different hardware, so treat it as a rough guide.
Can I run bekko-system-one or wald locally?
Yes, both: systemone pull hotchpotch/bekko-system-one and systemone pull org2ai/wald download the weights.
168 ms
Evaluation suite
The maker's short-input speed probe (4-option Choice, RTX 5090, 1 Oct 2026)
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
2026.09
1.2.0
Variants
0_BekkoInference
Dockerfile, LICENSE, NOTICE, model-files, reference, server
