Google DeepMind·released 2025-09-25
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 |
|---|---|---|---|
| WeirdML | 41.91accuracy (%) | unverified | 2025-09-25 |
| The Agent Company | 41.1accuracy (%) | unverified | 2025-09-25 |
| VPCT | 19.3accuracy (%) | unverified | 2025-09-25 |
| Terminal Bench | 17.1accuracy (%) | unverified· optimized | 2025-09-25 |