Gemini 2.0 Pro (Preview 02-05): benchmark results
February 5 Gemini 2.0 Pro preview snapshot. Provider: Google. Released 2025-02-05. Access: API.
Unified ELO 1582 ± 1, rank #315 of 1392 rated models, from 38 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| KOFFVQA - Korean Recognition | 90 | Score (%) | 95.7 |
| KOFFVQA - Commonsense Reasoning | 87.11 | Score (%) | 85.2 |
| KOFFVQA - Object Attributes | 80 | Score (%) | 80.2 |
| SEAL - Agentic Tool Use (Chat) | 57.86 | Score | 78.8 |
| KOFFVQA | 77.6 | Overall Score (%) | 78.4 |
| KOFFVQA - Document Understanding | 86 | Score (%) | 78.4 |
| Icelandic LLM - WikiQA-IS | 42.5 | Score (%) | 76.3 |
| Icelandic LLM - Belebele-IS | 93.11 | Score (%) | 75.8 |
| KOFFVQA - Korean OCR | 85 | Score (%) | 75.3 |
| Icelandic LLM - Inflection | 89.67 | Score (%) | 73.7 |
| KOFFVQA - Table Understanding | 78.67 | Score (%) | 71.6 |
| Icelandic LLM Leaderboard - Average | 77.99 | Average Score (%) | 69.9 |
Interactive version: theaggregate.ai/model?slug=gemini-2-0-pro-preview-02-05 · How It Works · Data refreshed daily, snapshot 2026-09-05.