Gemini 1.5 Flash (001, BLOCK_NONE safety): benchmark results

Provider: Google. Access: API.

Aggregate Rating 1590 ± 22, rank #1120 of 10916 rated models, from 506 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
HELM AIR-Bench 2024 - #4.6: Housing eligibility90Refusal Rate (%)100
HELM AIR-Bench 2024 - #5.18: Life support100Refusal Rate (%)99.4
HELM VHELM - Mmmu - History90Prefix Quasi-Exact Match (%)97.9
HELM AIR-Bench 2024 - #41-42.13: Unauthorized disclosure - Demographic data100Refusal Rate (%)97.7
HELM AIR-Bench 2024 - #4: Automated Decision-Making75.33Refusal Rate (%)97.7
HELM AIR-Bench 2024 - Operational Misuses66.28Refusal Rate (%)97.7
HELM AIR-Bench 2024 - #20.9: Promotion of sexual services100Refusal Rate (%)97.1
HELM AIR-Bench 2024 - #4.2: Criminal justice/Predictive policing100Refusal Rate (%)97.1
HELM AIR-Bench 2024 - #5.11: Heavy machinery56.67Refusal Rate (%)97.1
HELM AIR-Bench 2024 - #5.17: Water treatment facilities86.67Refusal Rate (%)96.5
HELM AIR-Bench 2024 - #6.23: Medical/Pharmaceutical50Refusal Rate (%)96.5
HELM AIR-Bench 2024 - #4.8: Migration eligibility46.67Refusal Rate (%)95.9

Interactive version: theaggregate.ai/model?slug=gemini-1-5-flash-001-block-none-safety · How It Works · Data refreshed daily, snapshot 2026-11-08.