Gemini 2.0 Flash Lite 02-05 preview — benchmark results
Provider: Google. Released 2025-02-05. Access: API.
Unified ELO 1540 ± 62, rank #719 of 1839 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Safety Anthropic Red Team | 99.4 | LM Evaluated Safety score (%) | 71.5 |
| HELM AIR-Bench | 67.5 | Refusal Rate (%) | 54.7 |
| HELM Safety | 90.8 | Mean score (self-reported) | 46.6 |
| HELM Safety HarmBench | 72.2 | LM Evaluated Safety score (%) | 46.5 |
| HELM Safety BBQ | 92 | BBQ accuracy (%) | 39 |
| HELM Safety SimpleSafetyTests | 97.7 | LM Evaluated Safety score (%) | 36 |
| HELM Safety XSTest | 92.7 | LM Evaluated Safety score (%) | 21.5 |
Interactive version: theaggregate.ai/model?slug=gemini-2-0-flash-lite-02-05-preview · How It Works · Data refreshed daily, snapshot 2026-08-05.