2026-08 · Aligned to live AA snapshot
Launch: Claude Opus 5
Claude Opus 5 launches; pricing tiers for Opus 5 / GPT-5.6. This month aligns with the live Artificial Analysis–style public snapshot on-site.
Score method：Scores are era-relative (month top ≈95–100) for landscape review — not official historical Artificial Analysis replays. From 2026-08, the latest month aligns with the live AA-style snapshot. Compare with the live overall intelligence public board
Month landscape board
| # | Model | Vendor | Era score | Elo≈ | Pricing | Highlight |
|---|---|---|---|---|---|---|
| 🥇 | Claude Opus 5 (max)NEW | Anthropic | 100 | 1380 | 高努力度任务成本 | AA Intelligence ~61 |
| 🥈 | Claude Fable 5NEW | Anthropic | 98 | 1370 | 高 | AA ~60 |
| 🥉 | GPT-5.6 Sol (max) | OpenAI | 97 | 1365 | 高 | AA ~59 |
| 4 | Kimi K3 (max) | Moonshot | 94 | 1345 | 中 | AA ~57 |
| 5 | Grok 4.5 (high) | xAI | 92 | 1335 | 中 | AA ~54 |
| 6 | DeepSeek 旗舰 | DeepSeek | 90 | 1320 | 极低 | 开源/低价档 |
Elo≈ is a LMSYS-style discussion-scale estimate for recap — not an official historical snapshot.
Era long-read for this month: Public vs private boards: AA intelligence vs on-site probes
Launches this month
- Claude Opus 5Anthropicapi
AA 公开榜领先档
Pricing changes
- Claude Opus 5 / GPT-5.6 · 分档定价
max/xhigh/high 努力度分档，任务成本差异大
- Claude Opus 5 / GPT-5.6 · AA 任务成本分档
见现网公榜 cost_per_task 字段
Benchmark context
Benchmark context: public discussion of Arena Elo, AA Intelligence, and open suites (GPQA / SWE-bench, etc.). This page is a narrative archive, not a live probe.
Some historical narratives remain bilingual; model names stay in original form.
Related tools
Clavue CLI / imux IDE / clavue-2.1
Clavue · CLI 与 Agent 平台
CLI / GUI Agent 运行时、设备登录、会员额度与 OpenAI 兼容 API（api.clavue.com）。开发脚本、CI 与本地工具一条链路。
打开 Clavue ↗imux · 原生 macOS AI IDE
Clavue 平台的原生 IDE：多 Agent 分屏、Ghostty 级终端、Agent Chat、浏览器自动化与 Supervisor——不是又一个 Electron 壳。
了解 imux ↗Clavue 2.1 · 产品级大模型
旗舰模型 clavue-2.1（及 fast / pro / rev）：适合复杂推理与长程 Agent 循环。Chat、imux、API 共用会员额度。
查看模型 ↗