Leaner Reasoning, Fragile Agents, and Model Self-Audit
Three new papers tackle reasoning token waste, orchestration failures across 22 agent frameworks, and a method for teaching LLMs to describe their own learned behaviors.
Articles Tagged "Benchmarks"
ERNIE 5.0
Baidu's ERNIE 5.0 combines 2.4 trillion parameters with native omni-modal design, landing at LMArena's top-10 globally and outpacing GPT-5 High on chart and document benchmarks.
EXAONE 4.5
LG AI Research's first open-weight vision-language model packs 33B parameters, 262K context, and STEM scores above GPT-5-mini - but ships under a non-commercial license.
Qwen3.6-Max-Preview
Alibaba's first closed-weights flagship Qwen ships with a 256K context window, tops six agentic coding benchmarks, and ranks third on the Artificial Analysis Intelligence Index.
GPT-Rosalind
OpenAI's first domain-specific reasoning model for biology and drug discovery, launched April 16 2026 as a US-only research preview with a 0.751 BixBench score.
Kimi K2.6
Moonshot AI's Kimi K2.6 is a 1T-parameter MoE with 32B active per token, 256K context, a 300-agent swarm running 4,000 coordinated steps, and the top SWE-Bench Pro score among open-weight models at 58.6%.
Alibaba's Qwen3.6-Max Ships Closed - Tops Six Coding Evals
Alibaba released Qwen3.6-Max-Preview on April 20 as its first closed-weights flagship, ranking third globally on the Artificial Analysis Intelligence Index while topping six coding benchmarks.
Distillation Leaks, Weak Agents, and Research Sabotage
New papers show distillation silently transfers unsafe behaviors, weak agents bottleneck multi-agent pipelines, and frontier AI can't reliably audit sabotaged ML research.
Kimi K2.6 - Open Weights, 300 Agents, Top Coding Score
Moonshot AI releases Kimi K2.6 under Modified MIT with open weights on HuggingFace, 300-agent swarm execution, and the highest SWE-Bench Pro score among open models.
Claude Opus 4.7 Review: Coding Giant, Mixed Signals
Claude Opus 4.7 leads SWE-bench and agent benchmarks but regresses on web research, inflates token costs by up to 35%, and trades prose quality for literal instruction-following.
Stanford 2026 AI Index - Cash In, Transparency Out
Stanford's 2026 AI Index shows global investment hitting $581B in 2025, while foundation model transparency scores fell by a third as capabilities raced ahead of governance.
Best AI Home Workstations 2026 - Full Buying Guide
Complete buying guide for AI home workstations in 2026 - pre-built machines and DIY builds for running local LLMs from 3B to 70B+ models, with benchmarks, part lists, and price-tier comparisons.
