Gemini 1.5 Flash-8B

Google

Vision ModelProprietary

Context

Release Date: Oct 03, 2024
Knowledge Cutoff: Aug 01, 2024
Window: 1M

PricingPer 1M tokens

Input: $0.0375
Output: $0.15
Blended 3:1: $0.065625

Capabilities

Speed: 280 t/s
Input
Output
Reasoning tokens

Latency

TTFT: 0.17 ms
500 token response: 1.95 s

Benchmarks

Intelligence: ●●○○○
Math: ●●○○○
Coding: ●○○○○
MMLU Pro: 56.9%
GPQA: 35.9%
HLE: 4.5%
SciCode: 22.9%
AIME: 3.3%
MATH 500: 68.9%
LiveCodeBench: 21.7%
HumanEval: 11.6%

Gemini 1.5 Flash-8B