Gemini 2.5 Pro 0605 Preview

Google

Frontier ModelReasoningVision ModelProprietary

Context

Knowledge Cutoff: Jan 01, 2025
Window: 1M

PricingPer 1M tokens

Input: $1.25
Output: $10
Blended 3:1: $3.4375

Capabilities

Speed: 143 t/s
Input
Output
Reasoning tokens

Latency

TTFT: 36.54 ms
500 token response: 40.02 s

Benchmarks

Reasoning: ●●●●○
Math: ●●●●●
Coding: ●●●○○
MMLU Pro: 86.2%
GPQA: 86.4%
HLE: 21.6%
SciCode: 42.8%
AIME: 88.0%
MATH 500: 93.0%
LiveCodeBench: 69.0%

Preview checkpoint, see latest.