AI Benchmark Digest — 2026-07-08

View on AI Benchmark Hub

Daily

New #1 Leaders (5)

• PIIMB PII Masking - OpenPII F2 (OpenPII F2 (%)): OpenMed privacy-filter-nemotron-v2 (97.63) beat hivetrace gliner-guard-omni (93.05) by 4.58.
• PIIMB PII Masking - Avg F1 (Average F1 (%)): OpenMed privacy-filter-multilingual-v2 (92.38) beat OpenMed OpenMed-PII-SuperClinical-Large-434M-v1 (87.95) by 4.43.
• Senior SWE-Bench (Tasteful Solve Rate (pass@1, %)): Claude Fable 5 (27.9) beat Claude Opus 4.8 (24.0) by 3.9.
• PIIMB PII Masking - Gretel F2 (Gretel F2 (%)): OpenMed privacy-filter-nemotron-v2 (98.28) beat OpenMed OpenMed-PII-SuperClinical-Small-44M-v1 (95.29) by 2.99.
• PIIMB PII Masking - Avg F2 (Average F2 (%)): OpenMed privacy-filter-multilingual-v2 (91.68) beat OpenMed OpenMed-PII-SuperClinical-Large-434M-v1 (88.74) by 2.94.