Gemini 1.0 Pro (002): benchmark results
Gemini 1.0 Pro 002 stable API snapshot. Provider: Google. Released 2024-02-01. Access: API.
Aggregate Rating 1482 ± 26, rank #2634 of 10916 rated models, from 410 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM AIR-Bench 2024 - #4.3: Adversely affects legal rights | 80 | Refusal Rate (%) | 86.6 |
| HELM AIR-Bench 2024 - #14.23: Physical characteristics | 100 | Refusal Rate (%) | 86 |
| pfgen-bench - QA Mode - Helpfulness | 0.4 | Helpfulness Score | 83 |
| HELM AIR-Bench 2024 - #39-40.39: Characterization of identity - Occupation | 1.67 | Refusal Rate (%) | 81.4 |
| HELM AIR-Bench 2024 - #8.7: Beautifying and whitewashing acts of war or aggression | 16.67 | Refusal Rate (%) | 80.8 |
| HELM Lite - WMT 2014 (cs-en) | 23.12 | BLEU-4 (%) | 80 |
| HELM Lite - WMT 2014 (de-en) | 20.54 | BLEU-4 (%) | 80 |
| HELM AIR-Bench 2024 - #14.16: Sexual orientation | 100 | Refusal Rate (%) | 77.9 |
| HELM AIR-Bench 2024 - #14.25: Personality | 97.22 | Refusal Rate (%) | 77.9 |
| pfgen-bench - QA Mode - Truthfulness | 0.89 | Truthfulness Score | 77.6 |
| HELM AIR-Bench 2024 - #14.31: Age | 100 | Refusal Rate (%) | 77.3 |
| HELM AIR-Bench 2024 - #14.26: Health conditions | 100 | Refusal Rate (%) | 76.2 |
Interactive version: theaggregate.ai/model?slug=gemini-1-0-pro-002 · How It Works · Data refreshed daily, snapshot 2026-11-08.