AIbase
EN
Home
AI Models Finder
Gemini 1.5 Pro (Sep '24)
G

Gemini 1.5 Pro (Sep '24)

Gemini 1.5 Pro is a medium-sized multimodal model optimized for a wide range of reasoning tasks. It can process large amounts of data at once, including 2 hours of video, 19 hours of audio, a codebase with 60,000 lines of code, or 2000 pages of text.
Intelligence(Medium)
Speed(Relatively Slow)
Input Supported Modalities
Yes
Is Reasoning Model
2,000,000
Context Window
8,192
Maximum Output Tokens
2023-11-01
Knowledge Cutoff
Go Compare

Pricing

￥18 /M tokens
Input
￥72 /M tokens
Output
￥15.75 /M tokens
Blended Price

Quick Simple Comparison

Input

Output

Gemini 2.0 Flash Thinking Experimental (Dec '24)
Gemini 1.5 Pro (Sep '24)
￥2.5
Gemini 2.0 Pro Experimental (Feb '25)

Basic Parameters

Gemini 1.5 Pro (Sep '24)Technical Parameters
Parameter Count
Not Announced
Context Length
2.0M tokens
Training Data Cutoff
2023-11-01
Open Source Category
Proprietary
Multimodal Support
Text, Image
Throughput
85
Release Date
2024-09-24
Response Speed
90.14,513 tokens/s

Benchmark Scores

Below is the performance of Gemini 1.5 Pro (Sep '24) in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
44.6
Large Language Model Intelligence Level
Coding Index
30.58
Indicator of AI model performance on coding tasks
Math Index
55.3
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
75
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
58.9
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
4.9
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
31.6
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
29.5
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
89.8
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
87.6
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
23
An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase