Tag: benchmark-evaluation
| # | Post Title | Date | User |
| Why did FigmaTrace lift GUI agent scores on six benchmarks? | 3 weeks ago | NHI Mgmt Group | |
| Why does trace analysis beat outcome-only evaluation for agent benchmarks? | 3 months ago | NHI Mgmt Group | |
| Are cost and latency now part of benchmark reliability in Cybench? | 3 months ago | NHI Mgmt Group | |