Google: Gemma 2 27B

Text input Text output
Author's Description

Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. See the [launch announcement](https://blog.google/technology/developers/google-gemma-2/) for more details. Usage of Gemma is subject to Google's [Gemma Terms of Use](https://ai.google.dev/gemma/terms).

Key Specifications
Cost
$$$$
Context
8K
Parameters
27B
Released
Jul 12, 2024
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Stop Presence Penalty Logit Bias Top P Temperature Min P Frequency Penalty Max Tokens
Performance Summary

Gemma 2 27B by Google demonstrates strong overall performance, particularly excelling in speed and reliability. It consistently ranks among the fastest models available and offers highly competitive pricing across various benchmarks. The model exhibits exceptional reliability, providing usable responses with minimal technical failures, achieving a 100th percentile ranking. In terms of specific benchmarks, Gemma 2 27B shows notable strengths in Ethics, achieving perfect 100% accuracy, making it the most accurate model at its price point and among models of comparable speed. It also performs very well in General Knowledge with 97% accuracy. Email Classification is another strong area, with 95% accuracy. However, the model shows significant weaknesses in Instruction Following, where it recorded 0% accuracy, indicating a critical area for improvement. Its performance in Coding (81% accuracy) and Reasoning (50% accuracy) is moderate, falling around the average for its peer group. While its speed is generally high, the duration for some benchmarks like Coding, Reasoning, and General Knowledge is in the higher percentiles, suggesting that while it's fast overall, certain complex tasks might take longer.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.8
Completion $0.8

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Together
Together | google/gemma-2-27b-it 8K $0.8 / 1M tokens $0.8 / 1M tokens
NextBit
NextBit | google/gemma-2-27b-it 8K $0.65 / 1M tokens $0.65 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by google