Articles

15 articles
Tag: benchmark ✕
REDMAGIC 11 Pro Delisted from 3DMark After Benchmark Manipulation Detection Tech
2026-04-10T15:56:39.912Z · Src: 2026-04-10T00:00:00.000Z
redmagicnubiabenchmark
New Benchmark Tests AI Agents on Long-Horizon Real-World Financial Tasks Business
2026-04-08T07:29:59.724Z · Src: 2026-04-08T00:00:00.000Z
aifinancebenchmark
CARE Framework: Evaluating AI Therapy Responses Against Six Core Psychotherapeutic Principles AI
2026-04-08T06:22:46.300Z · Src: 2026-04-08T00:00:00.000Z
aimental healththerapy
PhageBench: Testing Whether LLMs Can Understand Raw Bacteriophage Genomes Science
2026-04-08T05:14:55.039Z · Src: 2026-04-08T00:00:00.000Z
llmgenomicsbiology
Claw-Eval: Toward Trustworthy Evaluation of Autonomous AI Agents AI
2026-04-08T04:40:08.997Z · Src: 2026-04-08T00:00:00.000Z
aiagentsbenchmark
From Hallucination to Scheming: First Unified Taxonomy of LLM Deception Across 50 Benchmarks AI
2026-04-08T01:49:35.018Z · Src: 2026-04-07T00:00:00.000Z
llm deceptionhallucinationscheming
IEEE Spectrum Deep Dive: The Challenge of Benchmarking AGI Progress AI
2026-04-04T14:47:53.652Z · Src: 2026-04-04T00:00:00.000Z
agibenchmarkopenai
ArXiv Spotlight: User Turn Generation as a Probe of Interaction Awareness in LLMs AI
2026-04-03T12:38:30.770Z · Src: 2026-04-03T00:00:00.000Z
aillmresearch
AGI Benchmarks: Why Tracking Progress Toward Artificial General Intelligence Remains Extraordinarily Difficult AI
2026-03-29T22:28:44.237Z · Src: 2026-03-29T00:00:00.000Z
agibenchmarkai
Why Video Games Still Baffle AI Models: Julian Togelius on the Limits of LLM Intelligence AI
2026-03-29T22:26:27.184Z · Src: 2026-03-29T00:00:00.000Z
aillmvideogames
KDE Plasma 6.6 Outperforms GNOME 50 on Linux Gaming Benchmarks With AMD and Nvidia Tech
2026-03-29T02:05:33.377Z · Src: 2026-03-28T00:00:00.000Z
kdegnomelinux
KDE Plasma 6.6 Beats GNOME 50 in Linux Benchmarks on Both AMD and Nvidia Tech
2026-03-28T17:28:16.241Z · Src: 2026-03-28T00:00:00.000Z
linuxkdegnome
Symbolica's Agentica SDK Achieves 36% on ARC-AGI-3 Day 1, Crushing CoT Baselines at 1/9th Cost AI
2026-03-27T02:16:32.996Z · Src: 2026-03-27T00:00:00.000Z
aiarc agi 3symbolica
ARC-AGI-3: The Next Frontier of Artificial General Intelligence Benchmarking AI
2026-03-26T00:19:50.000Z · Src: 2026-03-26T00:00:00.000Z
ARC Prize announces ARC-AGI-3, the third iteration of its influential AGI benchmark testing novel visual reasoning. The new version features more complex puzzles and a higher difficulty ceiling for ev
agiarcbenchmark
Qwen3.5-9B on MacBook M5 Scores 93.8% vs GPT-5.4's 97.9% on Security Benchmark AI
2026-03-20T20:34:30.000Z
A new HomeSec-Bench benchmark shows Qwen3.5-9B running locally on a MacBook Pro M5 achieves 93.8% accuracy on security tasks, just 4 points behind GPT-5.4 cloud — with zero API costs and full privacy.
ailocal aiqwen