Gemini 1.5 Flash-8B (001): benchmark results
Gemini 1.5 Flash-8B 001 stable API snapshot. Provider: Google. Released 2024-10-03. Access: API.
Aggregate Rating 1497 ± 23, rank #791 of 1656 rated models, from 163 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Norwegian Common Sense Reasoning | 88.45 | Common Sense Reasoning Average Score (%) | 97 |
| KOFFVQA - Document Understanding | 91.33 | Score (%) | 90.1 |
| Open Portuguese LLM - ENEM | 76.42 | Accuracy (%) | 90 |
| Open Portuguese LLM - OAB Exams | 56.04 | Accuracy (%) | 89.1 |
| Open Portuguese LLM - ASSIN2 RTE | 93.29 | Macro F1 (%) | 88.2 |
| Open Portuguese LLM - FaQuAD NLI | 79.37 | Macro F1 (%) | 87 |
| EuroEval Icelandic NLU - Hotter and Colder Sentiment | 52.23 | Matthews correlation coefficient (%) | 86.7 |
| EuroEval Faroese NLU - FoSent | 59.31 | Matthews correlation coefficient (%) | 85.7 |
| Open Portuguese LLM - BLUEX | 64.67 | Accuracy (%) | 85.3 |
| EuroEval Spanish NLU - Sentiment Headlines ES | 48.7 | Matthews correlation coefficient (%) | 83.3 |
| EuroEval Icelandic NLU - ScaLA IS | 25.55 | Matthews correlation coefficient (%) | 80.6 |
| EuroEval Dutch NLU - ScaLA NL | 54.14 | Matthews correlation coefficient (%) | 74 |
Interactive version: theaggregate.ai/model?slug=gemini-1-5-flash-8b-001 · How It Works · Data refreshed daily, snapshot 2026-10-20.