Gemini 2.5 Pro

Google DeepMind · google/gemini-2-5-pro

ProviderGoogle DeepMind
Familygemini-pro
Typellm-reasoning
Statusactive
Released2025-03-20
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 Benchmarkunassessed71.2
AIME 2025unassessed86.7
AlpacaEvalunassessed51.5
Arena Elo — Codingunassessed1370.0
Arena Elo — Hard Promptsunassessed1460.5
Arena Elo — Mathunassessed1400.0
Arena Elo — Overall (Text)unassessed1380.0
Arena Elo — Style Controlunassessed1448.2
Arena Elo — Visionunassessed1246.0
Artificial Analysis Intelligence Indexunassessed85.0
Artificial Analysis Output Speedunassessed71.0
BBQ (Bias Benchmark for QA)unassessed84.2
ChartQAunassessed87.5
DocVQAunassessed93.8
FinBenchunassessed69.8
FLORES English-to-Germanunassessed63.2
FLORES English-to-Spanishunassessed68.1
FLORES English-to-Japaneseunassessed58.1
FLORES English-to-Chineseunassessed56.8
GPQA Diamondunassessed80.5
GSM8Kunassessed90.8
HELM Safetyunassessed88.5
HumanEvalunassessed91.2
IFEvalunassessed91.0
LegalBenchunassessed73.8
LiveCodeBenchunassessed57.8
MATH-500unassessed95.2
MathVistaunassessed67.8
MedQAunassessed80.2
MGSM (Multilingual Grade School Math)unassessed87.5
MMLU: Astronomyunassessed79.8
MMLU: Biology (subcategory)unassessed87.2
MMLU: Business Ethicsunassessed81.2
MMLU: Chemistry (subcategory)unassessed81.5
MMLU: Clinical Knowledgeunassessed86.5
MMLU: Computer Science (subcategory)unassessed87.8
MMLU: Jurisprudenceunassessed79.2
MMLU: Physics (unresolved key)unassessed84.8
MMLU-Prounassessed84.0
MMLU: Professional Accountingunassessed71.2
MMLU: Professional Lawunassessed77.2
MMMUunassessed72.1
MT-Benchunassessed9.2
MultiPL-Eunassessed84.9
MultiPL-E: C++unassessed84.2
MultiPL-E: C#unassessed84.8
MultiPL-E: Gounassessed81.2
MultiPL-E: Javaunassessed87.8
MultiPL-E: JavaScriptunassessed87.5
MultiPL-E: Juliaunassessed67.2
MultiPL-E: Kotlin (unconfirmed)unassessed79.2
MultiPL-E: Luaunassessed61.8
MultiPL-E: Perlunassessed58.5
MultiPL-E: PHPunassessed82.5
MultiPL-E: Pythonunassessed91.8
MultiPL-E: Runassessed64.8
MultiPL-E: Rubyunassessed74.2
MultiPL-E: Rustunassessed75.5
MultiPL-E: Scalaunassessed68.5
MultiPL-E: Swiftunassessed72.5
MultiPL-E: TypeScriptunassessed86.5
OCRBenchunassessed85.2
SWE-bench Agentunassessed55.5
SWE-bench Verifiedunassessed63.8
τ-benchunassessed58.2
Terminal-Benchunassessed45.5
ToxiGenunassessed91.5
WildBenchunassessed79.8

Data

This card as JSON · Edit on GitHub