Amazon·released 2024-12-03
Scored on 4 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 |
|---|---|---|---|
| MMLU | 76accuracy (%) | unverified· optimized | 2024-12-03 |
| Lech Mazur Writing | 60.5accuracy (%) | unverified | 2024-12-03 |
| The Agent Company | 1.7accuracy (%) | unverified | 2024-12-03 |
| HLE | 0accuracy (%) | unverified | 2024-12-03 |