diff --git a/README.en.md b/README.en.md index aaf642c..ab2a7c9 100644 --- a/README.en.md +++ b/README.en.md @@ -18,6 +18,7 @@ One-shot LLM eval cases by NAGI STUDIO: same prompt, different model x harness x |---|---|---|---|---| | Claude Fable 5 | Anthropic | Claude Web App | Max | 02 | | Claude Fable 5 | Anthropic | Claude Code | Max | 02 | +| Claude Opus 4.8 | Anthropic | Claude Code | Max | 01 | | GPT-5.5 Pro | OpenAI | ChatGPT Web | Extended Pro | 02 | | GPT-5.5 | OpenAI | Codex CLI (no skills) | xhigh | 02 | | Gemini 3.1 Pro | Google | AntiGravity | High | 02 | @@ -33,7 +34,7 @@ One-shot LLM eval cases by NAGI STUDIO: same prompt, different model x harness x | Kimi K2.6 | Moonshot AI | Kimi Code (local) | Thinking | 02 | | MiniMax M3 | MiniMax | MiniMax Code Web | Thinking | 01 | -Pending: Claude Opus 4.8 · Mistral Medium 3.5 · GLM-5.1 · Qwen3.7-Max (PRs welcome) +Pending: Mistral Medium 3.5 · GLM-5.1 · Qwen3.7-Max (PRs welcome) > This table is a hand-maintained snapshot; the site's registry section is generated live from `models/*.json` and is authoritative. diff --git a/README.md b/README.md index b321b82..dda23c5 100644 --- a/README.md +++ b/README.md @@ -18,6 +18,7 @@ NAGI STUDIO 的 LLM 测评案例集:同一段提示词,不同「模型 × Ha |---|---|---|---|---| | Claude Fable 5 | Anthropic | Claude 网页版 | Max | 02 | | Claude Fable 5 | Anthropic | Claude Code | Max | 02 | +| Claude Opus 4.8 | Anthropic | Claude Code | Max | 01 | | GPT-5.5 Pro | OpenAI | ChatGPT 网页版 | Extended Pro | 02 | | GPT-5.5 | OpenAI | Codex CLI(无 skill) | xhigh | 02 | | Gemini 3.1 Pro | Google | AntiGravity | High | 02 | @@ -33,7 +34,7 @@ NAGI STUDIO 的 LLM 测评案例集:同一段提示词,不同「模型 × Ha | Kimi K2.6 | Moonshot AI | Kimi Code(本地) | Thinking | 02 | | MiniMax M3 | MiniMax | MiniMax Code 网页版 | Thinking | 01 | -待测:Claude Opus 4.8 · Mistral Medium 3.5 · GLM-5.1 · Qwen3.7-Max(欢迎 PR 补充) +待测:Mistral Medium 3.5 · GLM-5.1 · Qwen3.7-Max(欢迎 PR 补充) > 此表为人工维护的快照;站点上的「模型阵容」表由 `models/*.json` 实时生成,以站点为准。 diff --git a/models/claude-opus-4-8.json b/models/claude-opus-4-8.json index 6043309..fc9d18f 100644 --- a/models/claude-opus-4-8.json +++ b/models/claude-opus-4-8.json @@ -5,10 +5,12 @@ "runs": { "pelican-cycling": { "note": { - "zh": "以 Claude Opus 4.8 一次生成;运行环境与思考档位待维护者补充。", - "en": "Generated in one shot by Claude Opus 4.8; harness and effort level to be confirmed by the maintainer." + "zh": "在 Claude Code 中以 Claude Opus 4.8(Max 思考配额)一次生成。", + "en": "Generated in one shot by Claude Opus 4.8 (Max effort) inside Claude Code." }, "contributor": "Nagi-ovo" } - } + }, + "harness": "Claude Code", + "effort": "Max" }