AsymLoop - Five-shot - SIQA: leaderboard
AsymLoop (2026): research-trained Dense,Full LoopK2 andAsymLoopK3 at matched effective depth; scale labels follow paper, with1.68B/3B/7B/20Btraining tokens. LM Evaluation Harness Five-shot downstream accuracy; unrelated public checkpoints are not aliases. Accuracy (%).
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | AsymLoop Study 1B AsymLoop K3 Base | 43.65 | |
| 2 | AsymLoop Study 1B Full Loop K2 Base | 43.09 | |
| 3 | AsymLoop Study 1B Dense Base | 42.48 | |
| 4 | AsymLoop Study 350M AsymLoop K3 Base | 40.69 | |
| 5 | AsymLoop Study 350M Full Loop K2 Base | 39.15 | |
| 6 | AsymLoop Study 350M Dense Base | 39 | |
| 7 | AsymLoop Study 135M Full Loop K2 Base | 38.33 | |
| 8 | AsymLoop Study 135M AsymLoop K3 Base | 37.56 | |
| 9 | AsymLoop Study 135M Dense Base | 36.44 | |
| 10 | AsymLoop Study 60M AsymLoop K3 Base | 36.13 |
Interactive version: theaggregate.ai/benchmark?slug=asymloop-five-shot-siqa · How It Works · Data refreshed daily, snapshot 2026-10-22.