Gemma 2 9B

Gemma 2 9B IT is an instruction-tuned version of Google's Gemma 2 9A base model. It was trained on 8 trillion tokens of web data, code, and mathematical content. The model features sliding window attention, logit soft capping, and knowledge extraction techniques. It is optimized for conversational applications through supervised fine-tuning using WARP, distillation, RLHF, and model merging.

Intelligence(Relatively Weak)

Speed(Slow)

Input Supported Modalities

Is Reasoning Model

8,192

Context Window

8,192

Maximum Output Tokens

Knowledge Cutoff

Go Compare

Pricing

- /M tokens

Input

- /M tokens

Output

￥1.44 /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

Gemma 2 9BTechnical Parameters

Parameter Count

9,240.0M

Context Length

8,192 tokens

Training Data Cutoff

Open Source Category

Open Weights (Permissive License)

Multimodal Support

Text Only

Throughput

Release Date

2024-06-27

Response Speed

0 tokens/s

Benchmark Scores

Below is the performance of Gemma 2 9B in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.

Intelligence Index

Large Language Model Intelligence Level

22.2

Large Language Model Intelligence Level

Coding Index

Indicator of AI model performance on coding tasks

6.64

Indicator of AI model performance on coding tasks

Math Index

Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks

25.87

Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks

MMLU Pro

Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video

49.5

Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video

GPQA

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions

31.1

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions

HLE

The model's comprehensive average score on the Hugging Face Open LLM Leaderboard

3.9

The model's comprehensive average score on the Hugging Face Open LLM Leaderboard

LiveCodeBench

Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems

12.6

Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems

SciCode

The model's capability in code generation for scientific computing or specific scientific domains

0.7

The model's capability in code generation for scientific computing or specific scientific domains

HumanEval

Score achieved by the AI model on the specific HumanEval benchmark test set

65.4

Score achieved by the AI model on the specific HumanEval benchmark test set

Math 500 Score

Score on the first 500 larger, more well-known mathematical benchmark tests

51.7

Score on the first 500 larger, more well-known mathematical benchmark tests

AIME Score

An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)

Output tokens/million

Output tokens/million

Output tokens/million

Output tokens/million

Output tokens/million

131k

Context Length

Gemini 2.0 Flash Lite (Preview)

Output tokens/million

Output tokens/million

33k

Context Length

Qwen2.5 Coder Instruct 32B

Output tokens/million

131k

Context Length

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご