Anthropic: Claude Opus 4.8
Chatanthropic/claude-opus-4.8Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters. It is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.
供应商
/v1/chat/completions/v1/responses程式碼範例
import anthropicclient = anthropic.Anthropic(base_url="https://api.ofox.io/anthropic",api_key="YOUR_OFOX_API_KEY",)message = client.messages.create(model="anthropic/claude-opus-4.8",max_tokens=1024,messages=[{"role": "user", "content": "Hello!"}],)print(message.content[0].text)
運行狀態
第三方評測
Anthropic: Claude Opus 4.8 在 LMArena 文字榜單(風格控制) 綜合類別中獲得 1475 分,在 374 個模型中排名第 16,基於 27,803 次人類偏好投票(更新於 2026-07-12)。
| 類別 | Arena 分數 | 95% 信賴區間 | 排名 | 投票數 |
|---|---|---|---|---|
| 綜合 | 1470–1481 | 第 16 / 374 名 | 27,803 | |
| 困難任務 | 1501–1514 | 第 8 / 374 名 | 18,352 | |
| 程式設計 | 1525–1541 | 第 8 / 369 名 | 7,749 | |
| 數學 | 1462–1494 | 第 19 / 362 名 | 1,336 | |
| 創意寫作 | 1452–1471 | 第 14 / 372 名 | 4,852 | |
| 指令遵循 | 1471–1486 | 第 11 / 374 名 | 9,428 | |
| 中文 | 1512–1546 | 第 9 / 344 名 | 1,295 |
來源:LMArena · CC BY 4.0 · 更新於 2026-07-12 · 評測方法 ↗ · 排名為 LMArena 文字榜單(風格控制) 各類別內的比較,分數來自第三方人類偏好評測,並非 OFOX 官方評分。