Independent measured model card
SlayerLab/Slayer149-Balanced-ARC-E-ft-45500
Hugging Face source ↗ · JSON for agents
149.3M unique parameters (e7d4b8dea441)
Every result links to its execution evidence. Compare scores only within matching protocols; no overall best-model claim. GPU-slot time includes evaluator setup and CPU work.
All current benchmark results
| Benchmark / coverage | Result | Version / protocol | GPU-slot time | Evidence |
|---|---|---|---|---|
| ARC-Challenge subset · 32 items | 28.12% accuracy · max | e7d4b8dea441codesota-sub1b-choice-v1 | 4.9s | Inspect run · Manifest |
| ARC-Easy subset · 32 items | 62.50% accuracy · max | e7d4b8dea441codesota-sub1b-choice-v1 | 5.1s | Inspect run · Manifest |
| ARC-Easy (full test split, raw accuracy) full · 2,376 items | 59.34% accuracy · max | e7d4b8dea441codesota-sub1b-arc-easy-standard-v2 | 87.1s | Inspect run · Manifest |
| BoolQ subset · 32 items | 78.12% accuracy · max | e7d4b8dea441codesota-sub1b-choice-v1 | 7.2s | Inspect run · Manifest |
| HellaSwag subset · 32 items | 37.50% accuracy · max | e7d4b8dea441codesota-sub1b-choice-v1 | 5.2s | Inspect run · Manifest |
| OpenBookQA subset · 32 items | 21.88% accuracy · max | e7d4b8dea441codesota-sub1b-choice-v1 | 5.0s | Inspect run · Manifest |