Loading activity…
@artificialanlys
Independent analysis of AI
AI
Standard pricing is $8 per million input tokens and $40 per million output tokens, with an optional fast mode.
AI
His early-access testing favored one agent for coding projects, but clear goals and human oversight still mattered.
AI
With both models at max effort, Ember matched Claude Haiku 5.5’s Intelligence Index score at roughly one-third the task cost.
AI
Private datasets now carry 45% of the index’s weight, up from 25% in the first version.
AI
The model supports image inputs, with fine-tuning and inference available at launch and downloadable weights planned for later.
AI
ChatGPT Images 2.6 can turn prompts and pictures into animated GIFs and lets users keep reference images for reuse.
AI
Kimi K3.1 Pro's trait percentile ranks shifted 30 points on average from Kimi K3's, Artificial Analysis found.
AI
AA-Omniscience v1.1 has 3,000 questions and a new 300-question public set calibrated to match the private set's difficulty.
AI
Artificial Analysis says Astra used 514 arm moves in 13 minutes; Claude used 3,270 moves in 34 minutes.
XAI
Artificial Analysis ranks its High configuration first on a 22-model index but eighth for live-conversation preference.
AI
Artificial Analysis scores the high-reasoning model at 26 on its Intelligence Index v5, up from Preview's 25.
Technology
Mistral says Le Chonk ranks first among open models on Cognition’s FrontierCode benchmark.
AI
Mistral announced the weights after a public preview, but its linked main Hugging Face listing showed “Upcoming release.”
AI
ArtificialAnlys says Muse Spark 1.3 scores 100 for friendliness, while GPT-6 Sol scores 100 for directness.
AI
A post also thanked participants in a fireside chat at the October 27 launch event.
AI
NVIDIA describes speaker attribution and translation in one checkpoint; SiliconANGLE reports a demo and downloadable checkpoint.
XAI
GitHub says it commissioned and funded the evaluation; Artificial Analysis measures average pay-per-token API cost per task across the index.
AI
One poster suggests OpenAI has the best reinforcement learning—or that its models perform poorly without reasoning.
AI
AssemblyAI lists AssemblyAI-TTS-1 at $15 per million input characters and quotes 90 ms to first audio in production.
YouTubeAI
Satya Nadella says Copilot’s unified harness is now in Foundry, a managed service for long-running agents.
