Healthcare
AI Drug Discovery: SandboxAQ, Tazbentetol, and New
SandboxAQ integrated its physics-grounded drug discovery models into Anthropic's Claude this week, while schizophrenia drug tazbentetol…
Tag: AI benchmarks
OpenAI
AI Benchmarks Under Fire: Hacks, IQ Scores, and New Records
A new AI IQ scoring site mapping 50+ models onto a human intelligence scale drew both…
AI Agents
AI Drug Discovery Gets Smarter in 2025
SandboxAQ has integrated physics-based molecular models into Anthropic's Claude, lowering the barrier to AI-assisted drug discovery.…
Enterprise
AI Benchmarks Under Scrutiny: Hacks, IQ Scores, and OpenAI’s
A new automated tool called BenchJack found 219 reward-hacking exploits across 10 major AI agent benchmarks,…
AI
AGI Milestones in 2026: Benchmarks, Reasoning, and the Gaps
In 2026, Recursive Language Models are topping long-context benchmarks with a shared-context architecture, a contested AI…
Enterprise
AI IQ Scores 50+ Models, Sparks Benchmark Debate
A startup project called AI IQ has mapped 50+ frontier language models onto a human IQ…
OpenAI
AI Benchmarks Under Fire: Reward Hacks, IQ Scores, and Parameter Golf
A new site assigning IQ scores to 50+ AI models drew praise and sharp criticism this…
OpenAI
AI Benchmarks Under Fire: Hacking, IQ Scores, and Parameter
A new automated auditing tool called BenchJack found 219 reward-hacking exploits across 10 popular AI agent…
AI
AI IQ Site Ranks 50+ Models on Human Intelligence Scale
A new AI IQ platform ranking 50+ language models on human intelligence scales has sparked debate,…
AI
AI IQ Site Sparks Debate Over Single-Score Model Rankings
A new AI IQ website ranking language models on human intelligence scales has sparked intense debate,…
Enterprise
AI Evaluation Costs Hit $40K Per Benchmark
AI evaluation costs have reached $40,000 per comprehensive benchmark run, creating a new bottleneck that limits…
SGI
AGI Research Milestones: Reasoning Models Show Patterns
Recent AGI research milestones include efficient 8B-parameter reasoning models matching larger systems, evidence that different models…