Gemini 2.5 Flash

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

ProviderGoogle DeepMind
Familygemini-flash
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
Aider Polyglot Benchmarkunassessed55.1
AIME 2025unassessed73.3
Arena Elo — Codingunassessed1330.0
Arena Elo — Hard Promptsunassessed1420.0
Arena Elo — Mathunassessed1350.0
Arena Elo — Overall (Text)unassessed1340.0
Arena Elo — Style Controlunassessed1411.0
Arena Elo — Visionunassessed1213.4
Artificial Analysis Intelligence Indexunassessed80.0
Artificial Analysis Output Speedunassessed87.0
FLORES English-to-Germanunassessed63.2
FLORES English-to-Spanishunassessed68.1
FLORES English-to-Japaneseunassessed58.1
FLORES English-to-Chineseunassessed56.8
GPQA Diamondunassessed70.2
GSM8Kunassessed86.2
HumanEvalunassessed88.8
IFEvalunassessed87.5
LiveCodeBenchunassessed49.5
MATH-500unassessed90.5
MGSM (Multilingual Grade School Math)unassessed82.6
MMLU-Prounassessed78.2
MultiPL-E: C#unassessed78.5
MultiPL-E: Juliaunassessed60.5
MultiPL-E: Kotlin (unconfirmed)unassessed71.5
MultiPL-E: Luaunassessed53.8
MultiPL-E: Perlunassessed49.5
MultiPL-E: PHPunassessed76.2
MultiPL-E: Runassessed56.2
MultiPL-E: Rubyunassessed64.5
MultiPL-E: Scalaunassessed58.8
MultiPL-E: Swiftunassessed64.8
SWE-bench Verifiedunassessed49.2

Data

This card as JSON · Edit on GitHub