Phil Stephens
223 posts













GLM-5.2 leads open weights models and sits at #3 overall on GDPval-AA, a real-world agentic work benchmark GLM-5.2 from @Zai_org scores 1524 Elo on GDPval-AA, which measures performance on real-world, economically valuable knowledge work through long-horizon, multi-turn tasks. Key takeaways: ➤ #3 overall, behind only Claude Fable 5 (1783) and Claude Opus 4.8 (1615), and level with GPT-5.5 (xhigh, 1509) ➤ The leading open weights model by a wide margin: the next open model, MiniMax-M3, scores 1408 ➤ Ahead of many proprietary models, including Google's Gemini 3.5 Flash (1357), Qwen 3.7 Max (1289), Muse Spark (1158) ➤ The tasks are agentic. GLM-5.2 averaged ~31 turns per task across 1,999 matches ➤ Consistent with the rest of its launch, GLM-5.2 also leads open weights on the Artificial Analysis Intelligence Index, ranks #3 on the Agentic Index, and #3 on AA-Briefcase







Snowy Hydro has conceded it may miss its 2028 deadline for finishing the Snowy 2.0 project and revealed its “disappointing” Italian contractor Webuild could suffer losses depending on the size of a major budget blowout. “The end of 2028 is not feeling comfortable,” Mr Barnes told The Australian on Thursday. “That’s probably that.” However, Mr Barnes disagreed with Webuild handing itself a high rating. “They’ve been a bit disappointing,” the Snowy chief executive said. “There’s been lots of things that they’ve had to deal with. They are pretty engaged with us. But it’s been challenging for them and it’s been challenging for us. Could they have done a better job? Probably.” Asked to elaborate, Mr Barnes said: “I think that’s probably best left to when we announce the new cost.” It's time to end the $40 billion+ Snowy 2.0 and Net Zero Scam.










