Back to Models
amazon logo
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
#129 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
#285
๐Ÿ‡ฏ๐Ÿ‡ตJapaneseELO: 1,184
#202
๐Ÿ‡จ๐Ÿ‡ณChineseELO: 1,272
#267
๐Ÿ‡ฐ๐Ÿ‡ทKoreanELO: 1,187
#220
๐Ÿ‡ฌ๐Ÿ‡งEnglishELO: 1,274
#282
frenchELO: 1,271
#222
germanELO: 1,260
#214
spanishELO: 1,269
#220
russianELO: 1,249
#275
๐Ÿ’ปCodingELO: 1,306
#274
๐ŸงฎMathELO: 1,244
#271
โœ๏ธCreative WritingELO: 1,221
#284
๐Ÿ“Instruction FollowingELO: 1,244
#284
๐ŸŒถ๏ธHard PromptsELO: 1,271
#280
๐Ÿ’ฌMulti-TurnELO: 1,229
#286
Vision
๐Ÿ†OverallELO: 1,019
#129