以下部分引用 AI 总结,现阶段 AI 仍然有幻觉。请以内容的原文为准。
数据新鲜度群聊 07-14 ✓卖方 07-14 ✓Wrap 断档15天 ✕News 07-15 ✓X 断档12天 ✕页面生成 07-15
GLM-5.2 (max)
4 atoms · 跨 2 天 · 首见 2026-06-18 · 最近 2026-06-23
三色: 🟦 fact 4 · 🟥 take 0 · stance ▲2/▼0/◆0
来源: X 2 · 卖 2
时态: fresh:4
标签: 好数字:4 · 好信源:2
事实 (fact) (4)
- 2026-06-23 · GDPval-AA v2 Leaderboard Elo rating
GLM-5.2 (max) achieves an Elo rating of 1524 on the GDPval-AA v2 Leaderboard, highlighted with an arrow.
tags: 好数字·好信源 · → daily
value: qty=1524 · date=2026-06-23
- 2026-06-23 · PACT 排名
GLM-5.2 (max) takes 4th place overall on PACT, a benchmark of negotiation skill in multi-round buyer-seller bargaining.
tags: 好数字·好信源 · → daily
value: qty=4th place overall
- 2026-06-23 · ranking on GDPval-AA benchmark
GLM-5.2 (max) sits at #3 overall on GDPval-AA, a real-world agentic work benchmark, even ahead of GPT-5.5 (xhigh).
tags: 好数字 · → daily
value: qty=3
- 2026-06-18 · cost per AA-Briefcase task
$2.40
tags: 好数字 · → daily
value: qty=$2.40 · date=2026-06-18
时间轴 (近 20)
- 2026-06-23 ·
fact · ranking on GDPval-AA benchmark · → daily
- 2026-06-23 ·
fact · GDPval-AA v2 Leaderboard Elo rating · → daily
- 2026-06-23 ·
fact · PACT 排名 · → daily
- 2026-06-18 ·
fact · cost per AA-Briefcase task · → daily
← 实体目录 · 系统日志