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 396M ModernBERT-large cross-encoder that answers typed questions about a text or a JSON state: one or several options, scores, yes/no with "not stated", spans with evidence quotes, rankings and numeric bins, each with a confidence and an act-or-escalate signal.
Decides
choice, noul, score
choice, score, noul, rank, extract
Architecture
bekko
solvi
Fine-tuned from
cross-encoder/ettin-reranker-400m-v1
answerdotai/modernbert-large
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
—
59.4%
Calibration error
—
0.210
Valid action rate
—
—
Median latency
5 ms
—
p95 latency
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 solvi?
bekko-system-one is from Yuichi Tateno (hotchpotch) and solvi from solvi. Both have open weights you can download and run. Both answer choice, noul and score questions. Only solvi answers rank and extract. bekko-system-one is the smaller model, at 395M parameters to 396M. bekko-system-one is licensed other; solvi, apache-2.0.
Which is more accurate, bekko-system-one or solvi?
Only solvi publishes an accuracy figure (59.4% on Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot); bekko-system-one does not, so there is no comparison to make without your own test.
Which is cheaper, bekko-system-one or solvi?
bekko-system-one: Free (open weights). solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bekko-system-one or solvi locally?
Yes, both: systemone pull hotchpotch/bekko-system-one and systemone pull solvi-ai/solvi download the weights.
5.4 ms
—
Evaluation suite
The maker's short-input speed probe (4-option Choice, RTX 5090, 1 Oct 2026)
Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot
