DeepSeek's first search test scores 69 points: fact-based question answering is near the top, while complex retrieval ranks third from the bottom.
52 minutes ago
Beating AI Express News: Independent evaluation firm Artificial Analysis tested DeepSeek’s newly launched search API, including it in a comparison of 27 search products, giving it an overall score of 69 and ranking 17th. The top two products, Exa and Perplexity, both scored 80 points. However, DeepSeek charges just $0.75 per 1,000 successful searches, making it the cheapest among all paid search APIs tested. The evaluation uniformly used GPT-5.6 Luna to call different search APIs to complete fact-based Q&A, in-depth research, and multi-round web searches. After integrating DeepSeek, the overall score rose from 33 points (when offline) to 69 points. DeepSeek performed well in direct fact-finding with an accuracy rate of 70%, just 3 percentage points behind the top-ranked product. But for complex problems requiring repeated searches and clue stitching, its accuracy rate was only 63%, ranking third from the bottom among the 27 products. Additionally, it returns an average of about 7,000 tokens per search. While this provides rich information, it increases the model’s cost of reading and processing materials. The average cost to complete one evaluation task is approximately $0.032, of which search fees account for only $0.0085, while model call fees reach $0.023, making up about 73% of the total cost—the second-highest model cost on the list. Even so, DeepSeek’s total cost per task is still the 5th cheapest. It has pushed search request prices to the lowest level, but lengthy search results have eroded part of its cost advantage.
Whale Tracking: Crude oil’s largest long position holder turned a loss into a profit, with intraday gains up $1.2 million.
10 minutes ago
Rising risk aversion grips global markets: South Korean stocks dropped over 4%, Bitcoin fell more than 2.7%, and Brent crude oil surged past $111.
10 minutes ago
Marathon Fusion has successfully achieved the "mercury-to-gold" alchemy, which could disrupt the fundamentals of gold in the medium to long term.
10 minutes ago
All Phase 4 staking pools for Renaiss's Earn collectible card staking yield product are fully subscribed, with a total of 1,593 Pokémon cards staked, valued at over $200,000.
10 minutes ago
A crypto whale liquidated a $21.15 million long position in Bitcoin, with the funds redirected to Ethereum.
10 minutes ago
Day 17 of OpenAI’s 28-day product sprint: Quota reset again.
10 minutes ago
Hot feeds
A trader profits $448K by monitoring #Binance's new listings!
2024.12.13 17:37:29
Last week, funds have flowed into #Bitcoin, #Ethereum, and #Hyperliquid.
2024.12.16 14:48:36
A $PEPE whale that had been dormant for 600 days transferred all 2.1T $PEPE($52M) to a new address.
2024.12.14 10:35:27
When Elon Musk tweeted about Moltbook, the meme coin MOLT experienced a short-term 30% price surge, hitting a new all-time high of $114 million.
2026.01.31 18:37:29
A smart #AI coin trader made $17.6M on $GOAT, $ai16z, $Fartcoin,$arc.
2025.01.05 16:05:18
A sniper earned 2,277 $ETH ($8.3M) trading $SHIRO within 18 hours!
2024.12.03 23:09:08
MoreHot Articles

How did I turn $1,000 into $30,000 with smart money?
2024.12.09

10 promising AI Agent cryptos
2024.12.05

The 30-Year-Old Entrepreneur Behind Virtual, a Multi-Million Dollar AI Agent Society
2025.01.22

10 smart traders specializing in MEMEcoin trading on Solana
2024.12.09

A trader lost $73.9K trading memecoins in just 3 minutes — a lesson for us all!
2024.12.13

What is $SPORE? Let us take you through the on-chain records to show you how it works.
2024.12.25

