Loading comparison…
HEAD TO HEAD
Andy Zhang: ajev and Dimitris Papadopoulos: biodecision, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | andy-zhang/ajev | lighteternal/biodecision |
|---|---|---|
| Summary | An open Jev-style decision model by Andy Zhang: a LoRA adapter on Gemma 4 26B-A4B (also on Gemma 4 12B) that reads a state and returns a temperature-calibrated probability for every option of a yes/no, choice or score question in one forward pass. | A 4B biomedical decision model by Dimitris Papadopoulos: Qwen3.5-4B tuned with Together AI's Tev1 recipe on 1.75M pharma, clinical-trial and literature decisions. One forward pass gives a temperature-scaled probability per option. Research use only. |
| Decides | choice, score, noul | choice, score, noul, classify |
| Architecture | ajev | biodecision |
| Fine-tuned from | google/gemma-4-26b-a4b-it | qwen/qwen3.5-4b |
| License | apache-2.0 | Research use only (several training sources are non-commercial); not validated for patient care |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | 75.3% |
| Calibration error | — | — |
| Valid action rate | — | — |
| Median latency | 49 ms | 39 ms |
| p95 latency | — | — |
| Evaluation suite | Sequential requests, the maker's own measurement | BioDecision v2 held-out test set (63,432 overlap-screened decisions from public biomedical benchmarks; the maker's own split) |
| Latest version | 2026.09 | 2.0.0 |
| Variants | — | LICENSE |
| Size of latest version | 141.9 MB | 8.7 GB |
| Files | 3 | 15 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, gemma, lora, calibrated, 26b | system-one, qwen, biomedical, clinical-trials, jev-inspired, research-only, 4b |
| Updated | Oct 7, 2026 | Oct 7, 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.
ajev is from Andy Zhang and biodecision from Dimitris Papadopoulos. Both have open weights you can download and run. Both answer choice, score and noul questions. Only biodecision answers classify. biodecision is the smaller model, at 4.0B parameters to 26B. ajev is licensed apache-2.0; biodecision, other.
Only biodecision publishes an accuracy figure (75.3% on BioDecision v2 held-out test set (63,432 overlap-screened decisions from public biomedical benchmarks; the maker's own split)); ajev does not, so there is no comparison to make without your own test.
ajev: Free (open weights). biodecision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, biodecision answers in about 39 ms at the median and ajev in about 49 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull andy-zhang/ajev and systemone pull lighteternal/biodecision download the weights.