Gemini 2.5 Pro Preview 06-05

Google DeepMind · google/gemini-2-5-pro-preview-06-05

ProviderGoogle DeepMind
Familygemini-pro
Typellm-reasoning
Statuspreview
Released2025-06-05
Updated2025-06-05

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)unassessed95.8
Aider Polyglot Benchmarkunassessed83.1
AIME 2025unassessed86.7
AlpacaEvalunassessed51.5
Arena Elo — Codingunassessed1370.0
Arena Elo — Mathunassessed1400.0
Arena Elo — Overall (Text)unassessed1380.0
Artificial Analysis Intelligence Indexunassessed85.0
Artificial Analysis Output Speedunassessed71.0
BBQ (Bias Benchmark for QA)unassessed84.2
ChartQAunassessed87.5
DocVQAunassessed93.8
FinBenchunassessed69.8
GPQA Diamondunassessed80.5
HELM Safetyunassessed88.5
HumanEvalunassessed91.2
IFEvalunassessed91.0
LegalBenchunassessed73.8
LiveCodeBenchunassessed57.8
MATH-500unassessed95.2
MathVistaunassessed67.8
MedQAunassessed80.2
MMLU-Prounassessed84.0
MMMUunassessed72.1
MT-Benchunassessed9.2
OCRBenchunassessed85.2
SWE-bench Verifiedunassessed63.8
ToxiGenunassessed91.5
WildBenchunassessed79.8

Data

This card as JSON · Edit on GitHub