OpenAI·released 2023-06-13
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 |
|---|---|---|---|
| Winogrande | 63.2accuracy (%) | unverified· optimized | 2023-06-13 |
| MMLU | 58.53accuracy (%) | unverified· optimized | 2023-06-13 |
| GSM8K | 57.77accuracy (%) | unverified· optimized | 2023-06-13 |
| BBH | 48.79accuracy (%) | unverified· optimized | 2023-06-13 |