All models
COMPARE
2 models, side by side.
What each one decides, how well calibrated it is, how fast it answers and what it costs to pull. Up to 4 at a time; the better value in each row is marked.
| Property | bespoke-labs/bespoke-nimble-9b | alibi-serikbay/jevk5 |
|---|---|---|
| Summary | An open Jev-style LoRA on Qwen3.5-9B from Bespoke Labs, trained on 2,676 contrastively curated examples to score the allowed answer tokens directly for enums, booleans and rubric levels. Recipe, data and a public benchmark suite are released with it. | Qwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF. |
| Decides | choice, noul, score, classify, route | choice, score, noul, classify, route |
| Architecture | nimble | jevk5 |
| Fine-tuned from | qwen/qwen3.5-9b | qwen/qwen3.5-4b |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights + hosted API | Open weights |
| Hosted by | Bespoke Labs | — |
| Input price | — | — |
| Decision accuracy | 90.1% | 78.4% |
| Calibration error | 0.054 | 0.035 |
| Valid action rate | — | — |
| Median latency | 106 ms | 13.2 ms |
| p95 latency | — | — |
| Evaluation suite | Bespoke held-out set (324 examples) | JevBench public hard tier |
| Latest version | 2026.09 | 0.3.0 |
| Variants | SHA256SUMS | SHA256SUMS |
| Size of latest version | 184.3 MB | 7.9 GB |
| Files | 10 | 8 |
| Downloads | 0 | 0 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, lora, curated-data, 9b | system-one, qwen, lora, distilled, 4b |
| Updated | Sep 25, 2026 | Sep 25, 2026 |