AA Intelligence Index Overhauls Benchmark: Claude Takes Top Spot, DeepSeek and GLM Lag 26 Points Behind
59 minutes ago
Beating AI News Flash: AI evaluation firm Artificial Analysis has significantly revised its Intelligence Index ranking. The new version adds 132 programming tasks from real open-source projects, requiring AI-generated code to not only pass tests but also meet the standards for project maintainers to accept and merge it. It also adds 70 research tasks, demanding AI complete actual research workflows in a terminal environment. To reduce the impact of models having seen test questions in advance, 60% of the new ranking’s scoring weight comes from private test sets or hidden answers. The top of the ranking remains dominated by Anthropic and OpenAI. Claude Opus 5.5 takes first place with 58 points, while GPT-6 Astra and GPT-6.1 Sol score 57 and 55 points respectively. Kimi K3.1 Pro earns 46 points, though its model weights are not yet open-source. DeepSeek V4.1 Flash and GLM-5.3, which have open-source weights, only score 32 points each — a full 26 points behind the leader, even lower than Claude Haiku 5.5’s 36 points. Among the new research tasks, GPT-6 Astra has a 63% completion rate, Kimi K3.1 Pro 34%, and DeepSeek V4.1 Flash just 13%. While GPT-6.1 Sol is 3 points lower than Claude Opus 5.5, when estimated via public API prices, it costs an average of $1.27 per comprehensive evaluation task, compared to $10.04 for the latter — nearly 8 times higher. The new version’s tasks also consume more tokens overall, with the median output tokens per task rising from 35,000 in the old version to 59,000.
A bizarre repository deletion incident unfolded on GitHub: A company acquired by Anthropic was conducting code cleanup, which caused customers’ code to vanish within two seconds, leading to initial suspicions of a hacker breach.
7 minutes ago
An ETH whale is suspected of offloading $12.41 million in holdings over the past half-month, which would result in a $148,000 loss if the sale is completed.
7 minutes ago
Amazon Earnings Preview: Focus on AWS' Robust Growth and Margin Recovery, Revenue Expected to Rise 12.25% Year-over-Year
7 minutes ago
Bitcoin options with a notional value of $10.92 billion will expire and settle this Friday, with a max pain price of $78,000.
7 minutes ago
Binance Wallet will launch the PREDICT presale event tomorrow.
7 minutes ago
The Initia Foundation has approved funding to cover the iUSD collateral shortfall, restoring its 1:1 peg.
7 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

