Rankings / Google DeepMind

Gemini 1.5 Pro

released 2025-02-15

BenchAtlas Index

as of 2026-07-14

Not enough benchmark coverage for a composite score (needs ≥4 families across ≥3 categories). The per-benchmark evidence below stands on its own — sparse coverage is an evidence gap, not a low score.

Benchmark evidence

5 results

multimodal

VISTA

37.1 %

35.7–38.4

independent

Scale Labs

reasoning math

ARC-AGI-2 split=semi_private · model_type=Base LLM	0.8 %	independent	ARC Prize Leaderboard
ARC-AGI-2 split=semi_private · model_type=Base LLM	0.0 usd_per_task	independent	ARC Prize Leaderboard
ARC-AGI-2 split=public_eval · model_type=Base LLM	0.0 usd_per_task	independent	ARC Prize Leaderboard
ARC-AGI-2 split=public_eval · model_type=Base LLM	0.0 %	independent	ARC Prize Leaderboard

Related variants

Gemini 1.5 Pro 001 Gemini 1.5 Pro 002