ArtificialAnlys

X · 45 atoms · 2026-06-23 → 2026-06-25 · 信用档先验 cred3

🟦 fact 44 · 🟥 take 1 · stance ▲0/▼0/◆1

覆盖实体 (top 10)

• HappyHorse-1.0 — 5 atoms
• AA-Briefcase — 4 atoms
• Claude Fable 5 — 4 atoms
• MAI-Image-2.5 — 4 atoms
• Grok Voice Think Fast 1.0 — 3 atoms
• GLM 5.2 — 3 atoms
• MAI-Image-2.5-Flash — 3 atoms
• Wan 2.7 — 3 atoms
• GPT-Realtime-2 (High) — 2 atoms
• Claude Opus 4.8 — 2 atoms

话题分布 (top 8)

任务耗时 (6) · 能力领跑 (6) · 模型评估 (4) · 基准测试 (4) · 模型表现 (4) · 模型排名 (4) · 模型评测排名 (3) · 智能体表现 (2)

样例 atoms

• 2026-06-24 · AA-Briefcase · Agentic knowledge work can take frontier models over 20 minutes per task, as measured in AA-Briefcase, our new benchmark
• 2026-06-24 · Claude Opus 4.8 · Claude Opus 4.8 is the highest-scoring available model, but it is also one of the slowest, taking ~23 minutes per task on average
• 2026-06-24 · Claude Opus 4.8 · Claude Opus 4.8 is the highest-scoring available model, but it is also one of the slowest, taking ~23 minutes per task on average
• 2026-06-24 · GPT-5.5 (xhigh) · GPT-5.5 (xhigh) in particular stands out as one of the most efficient top-performing models, using around half the time per task of Opus 4.8 (11 minutes) while ranking top 5 on the
• 2026-06-24 · GPT-5.5 (xhigh) · GPT-5.5 (xhigh) in particular stands out as one of the most efficient top-performing models, using around half the time per task of Opus 4.8 (11 minutes) while ranking top 5 on the

← Author 索引 · 实体目录