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 1609 ± 20, rank #460 of 1776 rated models, from 45 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
KOFFVQA - Korean Recognition90Score (%)95.7
KOFFVQA - Commonsense Reasoning87.11Score (%)85.2
KOFFVQA - Object Attributes80Score (%)80.2
SEAL - Agentic Tool Use (Chat)57.86Score78.8
KOFFVQA77.6Overall Score (%)78.4
KOFFVQA - Document Understanding86Score (%)78.4
Icelandic LLM - WikiQA-IS42.5Score (%)78
Icelandic LLM - Belebele-IS93.11Score (%)77.5
Icelandic LLM - Inflection89.67Score (%)75.3
KOFFVQA - Korean OCR85Score (%)75.3
KOFFVQA - Table Understanding78.67Score (%)71.6
Icelandic LLM Leaderboard - Average77.99Average Score (%)71.4

Interactive version: theaggregate.ai/model?slug=gemini-2-0-pro-preview-02-05 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.