Gemini 2.0 Flash (001) — benchmark results
Gemini 2.0 Flash 001 stable API snapshot. Provider: Google. Released 2025-02-05. Access: API.
Unified ELO 1596 ± 9, rank #481 of 1776 rated models, from 246 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Arcadia MMMU Open Ended | 39.62 | Accuracy (%) | 100 |
| CyberSecEval2 Interpreter Abuse | 33.5 | Accuracy (%) | 100 |
| CPTU Bench | 4.29 | Average Score (1-5) | 98.9 |
| KOFFVQA - Table Understanding | 96.67 | Score (%) | 98.1 |
| BRIDGE Medical Leaderboard - Few-Shot | 53.33 | Average Performance (%) | 97.2 |
| BRIDGE Medical Leaderboard | 46.11 | Average Performance (%) | 96.2 |
| BRIDGE Medical Leaderboard - CoT | 41.98 | Average Performance (%) | 95.3 |
| EuroEval Faroese NLU - FoSent | 71.36 | Sentiment classification Score (%) | 95 |
| Galileo Tool Tasks - BFCL v3 Multi-Turn Base Multi-Function | 91 | Accuracy (%) | 94.4 |
| Galileo Tool Tasks - BFCL v3 Multi-Turn Composite | 94 | Accuracy (%) | 94.4 |
| Galileo Tool Tasks - BFCL v3 Multi-Turn Missing Function | 93 | Accuracy (%) | 94.4 |
| Galileo Tool Tasks - Multi Turn | 93 | Accuracy (%) | 94.4 |
Interactive version: theaggregate.ai/model?slug=gemini-2-0-flash-001 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.