Claude Opus 4.8 (max)

8 atoms · 跨 3 天 · 首见 2026-06-15 · 最近 2026-06-23

三色: 🟦 fact 8 · 🟥 take 0 · stance ▲2/▼0/◆0

来源: X 7 · 卖 1

时态: fresh:8

标签: 好数字:8 · 好信源:1

事实 (fact) (8)

• 2026-06-23 · GDPval-AA v2 Leaderboard Elo rating
  Claude Opus 4.8 (max) achieves an Elo rating of 1615 on the GDPval-AA v2 Leaderboard.
  tags: 好数字·好信源 · → daily
  value: qty=1615 · date=2026-06-23
• 2026-06-22 · AA-Briefcase 单任务成本
  Claude Opus 4.8 (max) while costing 65% less
  tags: 好数字 · → daily
  value: qty=$6.86 · currency=USD · date=2026-06-22
• 2026-06-15 · 每任务时间
  Time per Intelligence Index task for leading models ranges from 1.5 minutes for Grok 4.3 (high) to 13.5 minutes for Claude Sonnet 4.6 (max). Claude Sonnet 4.6 takes longer per task than Claude Opus 4.8 (max) because it uses more output tokens to run the Intelligence Index. Gemini 3.1 Pro Preview stands out on the Intelligence vs Time per Intelligence Index Task chart at 1.6 minutes for an Intelligence Index of 46
  tags: 好数字 · → daily
  value: qty=6.4 分钟
• 2026-06-15 · GDPval-AA v2 Elo 评分
  GDPval-AA v2 is the highest weighted evaluation in the Intelligence Index v4.1. The upgrade re-baselines ELO to human performance at 1000, introduces a rotating panel of frontier-model judges, and raises the turn limit from 100 to 250 for longer-horizon agent trajectories. Claude Fable 5 (with fallback) leads at 1818, followed by Claude Opus 4.8 (1638). GPT-5.5 (xhigh) scores 1531. Claude Fable 5 is not currently available for use
  tags: 好数字 · → daily
  value: qty=1638
• 2026-06-15 · Intelligence Index v4.1 score
  Claude Opus 4.8 (max, 56) [is] the most intelligent available model
  tags: 好数字 · → daily
  value: qty=56 · date=2026-06-16
• 2026-06-15 · cost per Intelligence Index task
  Claude Opus 4.8 (max) is the most expensive available model at $1.78 per task
  tags: 好数字 · → daily
  value: qty=$1.78 · date=2026-06-16
• 2026-06-15 · cost per Intelligence Index task
  over 40x cheaper than Claude Opus 4.8 (max, $1.78)
  tags: 好数字 · → daily
  value: qty=$1.78 · date=2026-06-16
• 2026-06-15 · GDPval-AA v2 Elo score
  Claude Opus 4.8 (1638)
  tags: 好数字 · → daily
  value: qty=1638 · date=2026-06-16

时间轴 (近 20)

• 2026-06-23 · fact · GDPval-AA v2 Leaderboard Elo rating · → daily
• 2026-06-22 · fact · AA-Briefcase 单任务成本 · → daily
• 2026-06-15 · fact · 每任务时间 · → daily
• 2026-06-15 · fact · GDPval-AA v2 Elo 评分 · → daily
• 2026-06-15 · fact · Intelligence Index v4.1 score · → daily
• 2026-06-15 · fact · cost per Intelligence Index task · → daily
• 2026-06-15 · fact · cost per Intelligence Index task · → daily
• 2026-06-15 · fact · GDPval-AA v2 Elo score · → daily

← 实体目录 · 系统日志