Gemini 2.0 Flash (001): benchmark results
Gemini 2.0 Flash 001 stable API snapshot. Provider: Google. Released 2025-02-05. Access: API.
Aggregate Rating 1629 ± 8, rank #360 of 1656 rated models, from 442 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Arcadia MMMU Open Ended | 39.62 | Accuracy (%) | 100 |
| Complexity Ceiling Benchmark - Alien Grid | 22 | Accuracy (%; share of parseable trials whose final answer an | 100 |
| IsoSci | 62.2 | Accuracy (%; 288 problems forming 144 isomorphic cross-domai | 100 |
| Open Portuguese LLM - OAB Exams | 77.68 | Accuracy (%) | 99.3 |
| Open Portuguese LLM - ENEM | 87.89 | Accuracy (%) | 99 |
| Open Portuguese LLM - BLUEX | 80.39 | Accuracy (%) | 98.6 |
| KOFFVQA - Table Understanding | 96.67 | Score (%) | 98.1 |
| OpenCompass LLM - Instruction Following - Chinese (CompassBench 2501) | 74.6 | Score (%) | 97.4 |
| EuroEval Danish Knowledge - Danske Talemaader | 89.01 | MCC (x100) | 95.4 |
| EuroEval Faroese NLU - FoSent | 71.36 | Matthews correlation coefficient (%) | 95 |
| OpenCompass Knowledge - Engineering - English (CompassBench 2501) | 94 | Score (%) | 94.9 |
| Galileo Tool Tasks - BFCL v3 Multi-Turn Base Multi-Function | 91 | Accuracy (%) | 94.4 |
Interactive version: theaggregate.ai/model?slug=gemini-2-0-flash-001 · How It Works · Data refreshed daily, snapshot 2026-10-20.