Evaluation

Model-card benchmark evaluation suite (performance matrix)

Benchmark performance matrix reported in the model card (e.g., reasoning, coding, math, multimodal benchmarks); individual benchmark numbers are in a table not extracted into the corpus

General benchmark suites Google DeepMind — Gemini

Ask about this evaluation

How it was run

Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.

Gemini Ultra Model Card Dec 2023

Google DeepMind — Gemini

rich detail 8 method fields published

See how this test was run

Model card for Gemini 1.5 Pro and Flash Feb 2024

Google DeepMind — Gemini

rich detail 8 method fields published

See how this test was run

Gemini 2.0 Flash Model Card Dec 2024

Google DeepMind — Gemini

rich detail 7 method fields published

See how this test was run

Gemini 2.0 Flash-Lite Model Card Dec 2024

Google DeepMind — Gemini

rich detail 7 method fields published

See how this test was run

Gemini 2.5 Flash Model Card Mar 2025

Google DeepMind — Gemini

rich detail 10 method fields published

See how this test was run

Gemini 2.5 Flash-Lite Model Card Mar 2025

Google DeepMind — Gemini

rich detail 10 method fields published

See how this test was run

Gemini 2.5 Pro Model Card Mar 2025

Google DeepMind — Gemini

rich detail 10 method fields published

See how this test was run