Back to Models
amazon/nova-lite-v1
Not Available

Nova Lite 1.0

Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time customer interactions, document analysis, and visual question-answering tasks with high accuracy. With an input context of 300K tokens, it can analyze multiple images or up to 30 minutes of video in a single input.

12/5/2024
300,000 tokens
#121 Vision (Overall)
Specifications

Modalities

Input
text
image
Output
text

Supported Parameters

max_tokens
stop
temperature
tools
top_k
top_p

Max Output Tokens

5,120
Leaderboard
Text
๐Ÿ†OverallELO: 1,260
#280
๐Ÿ‡ฏ๐Ÿ‡ตJapaneseELO: 1,184
#202
๐Ÿ‡จ๐Ÿ‡ณChineseELO: 1,272
#263
๐Ÿ‡ฐ๐Ÿ‡ทKoreanELO: 1,187
#216
๐Ÿ‡ฌ๐Ÿ‡งEnglishELO: 1,274
#277
frenchELO: 1,270
#218
germanELO: 1,260
#215
spanishELO: 1,268
#217
russianELO: 1,249
#270
๐Ÿ’ปCodingELO: 1,306
#269
๐ŸงฎMathELO: 1,244
#267
โœ๏ธCreative WritingELO: 1,221
#279
๐Ÿ“Instruction FollowingELO: 1,244
#279
๐ŸŒถ๏ธHard PromptsELO: 1,271
#275
๐Ÿ’ฌMulti-TurnELO: 1,228
#281
Vision
๐Ÿ†OverallELO: 1,019
#121