Sub-100M parameter language models, same eval harness, transparent methodology.
| Model | Org | Params | WikiText-2 ↓ | BLiMP ↑ | ARC-Easy ↑ | Training Tokens | Links |
|---|---|---|---|---|---|---|---|
| Supra-50M-Instruct | SupraLabs | 51.8M | not reported | 76.3% | 52.2% | 20B | card base |
| GPT-S-5M | Axiomic Labs | 5.16M | 2.56 | 72.27% | 35.69% | 25B | card |
| Glint-1.3 (merged) | CompactAI | 982K | 3.08 | 68.7% | 32.5% | 100B | card |
| Supra-Mini-v5 | SupraLabs | 7.87M | 2.66 | 63.5% | 34.4% | — | card |
| Glint-1 | CompactAI | 1M | 4.07 | 61.2% | 32.0% | 100B | card |
| Supra-Mini-v4 | SupraLabs | 2.62M | 3.17 | 60.7% | 31.5% | — | card |
| Glint-0.4 | CompactAI | 1M | 5.24 | 58.5% | 31.0% | 10B | card |
| Supra-Mini-v3 | SupraLabs | 468K | 4.49 | 55.3% | 27.3% | — | card |
| Supra-Mini-v2 | SupraLabs | 168K | 7.79 | 53.5% | 26.8% | — | card |
| Glint-0.2 | CompactAI | 1M | TBD | 49.8% | 27.0% | ~100M | card |
| Glint-0.3 | CompactAI | 1M | TBD | 47.3% | 25.5% | ~100M | card |
| Glint-0.1 | CompactAI | 1M | TBD | 46.7% | 21.0% | ~100M | card |
| Shard-1 | CompactAI | 54.5M | TBD | TBD | TBD | ~20B | card |
| StorySupra-10M | SupraLabs | 12.6M | not reported | not reported | not reported | — | card |
| DistillSupra-0.2M | SupraLabs | 289K | not reported | not reported | not reported | — | card |
| MicroSupra-1k | SupraLabs | 1K | not reported | not reported | not reported | — | card |
| TrueMath | CompactAI | 1-layer | — | — | — | synthetic | card |
Open a PR on this Space with your model's benchmark results and reproduction steps. We require: params, training data provenance, eval harness used, and scores for at least 2 of the 3 benchmarks.