Gemini 1.5 Pro

Google DeepMind · google/gemini-1-5-pro

ProviderGoogle DeepMind
Familygemini-pro
Typevlm
Statusactive
Released2024-02-15
Updated2024-02-15

Reported benchmark scores

These scores carry one collection date for the whole card (2026-04) and a source list rather than a source per score, so they cannot be attributed individually. They are shown as reported and are not verified evidence. Benchmark pages carry the reviewed, dated evidence where it exists.
BenchmarkCatalogue standingScore
AI2D (AI2 Diagrams)unassessed82.5
AlpacaEvalunassessed24.4
Arena Elo — Codingunassessed1250.0
Arena Elo — Hard Promptsunassessed1350.2
Arena Elo — Mathunassessed1240.0
Arena Elo — Overall (Text)unassessed1260.0
Arena Elo — Style Controlunassessed1350.6
Arena Elo — Visionunassessed1178.6
Artificial Analysis Intelligence Indexunassessed78.0
Artificial Analysis Output Speedunassessed68.0
BBQ (Bias Benchmark for QA)unassessed82.8
ChartQAunassessed79.2
DocVQAunassessed88.5
FLORES English-to-Germanunassessed63.2
FLORES English-to-Spanishunassessed68.1
FLORES English-to-Japaneseunassessed58.1
FLORES English-to-Chineseunassessed56.8
GPQA Diamondunassessed55.8
GSM8Kunassessed90.8
HELM Safetyunassessed87.5
HumanEvalunassessed84.1
IFEvalunassessed82.0
MATH-500unassessed74.3
MathVistaunassessed55.8
MGSM (Multilingual Grade School Math)unassessed87.5
MMLU-Prounassessed72.0
MMMUunassessed62.8
ToxiGenunassessed91.2

Data

This card as JSON · Edit on GitHub