Gemini 1.5 Flash-8B

Google DeepMind · google/gemini-1-5-flash-8b

ProviderGoogle DeepMind
Familygemini-flash
Typevlm
Statusactive
Released2024-10-03
Updated2024-10-03

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
Arena Elo — Codingunassessed1220.0
Arena Elo — Hard Promptsunassessed1258.2
Arena Elo — Mathunassessed1210.0
Arena Elo — Overall (Text)unassessed1230.0
Arena Elo — Style Controlunassessed1258.1
Arena Elo — Visionunassessed1070.6
Artificial Analysis Intelligence Indexunassessed71.0
Artificial Analysis Output Speedunassessed86.0
BBQ (Bias Benchmark for QA)unassessed81.5
ChartQAunassessed74.8
DocVQAunassessed85.2
FLORES English-to-Germanunassessed63.2
FLORES English-to-Spanishunassessed68.1
FLORES English-to-Japaneseunassessed58.1
FLORES English-to-Chineseunassessed56.8
GPQA Diamondunassessed45.2
GSM8Kunassessed86.2
HELM Safetyunassessed86.2
HumanEvalunassessed78.5
IFEvalunassessed77.0
MATH-500unassessed65.8
MathVistaunassessed54.5
MGSM (Multilingual Grade School Math)unassessed82.6
MMLU-Prounassessed63.5
MMMUunassessed56.1
ToxiGenunassessed90.5

Data

This card as JSON · Edit on GitHub