Prime Intellect·released 2024-11-29
Scored on 6 benchmarks. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Every score, ranked, colored by evidence status.
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| HellaSwag | 61.89accuracy (%) | self-reported· optimized | 2024-11-29 |
| ARC AI2 | 39.36accuracy (%) | self-reported· optimized | 2024-11-29 |
| GSM8K | 38.58accuracy (%) | self-reported· optimized | 2024-11-29 |
| MMLU | 33.19accuracy (%) | self-reported· optimized | 2024-11-29 |
| Winogrande | 31.64accuracy (%) | self-reported· optimized | 2024-11-29 |
| BBH | 13.13accuracy (%) | self-reported· optimized | 2024-11-29 |