diff --git a/README.en.md b/README.en.md index 4ac4d07..2a7de96 100644 --- a/README.en.md +++ b/README.en.md @@ -34,7 +34,7 @@ One-shot LLM eval cases by NAGI STUDIO: same prompt, different model x harness x | Claude Opus 4.7 | Anthropic | Cursor · Max | 02 | | Claude Opus 4.6 | Anthropic | Cursor · Max | 02 | | Claude Opus 4.5 | Anthropic | Cursor · Thinking | 02 | -| Claude Sonnet 4.6 | Anthropic | Cursor · High | 01 | +| Claude Sonnet 4.6 | Anthropic | Claude Code · Max
Cursor · High | 03 | | GPT-5.5 Pro | OpenAI | ChatGPT Web · Extended Pro | 02 | | GPT-5.5 | OpenAI | Codex CLI · xhigh | 02 | | GPT-5.4 | OpenAI | Cursor · xhigh
Codex CLI · xhigh | 05 | diff --git a/README.md b/README.md index 7df7be7..501f195 100644 --- a/README.md +++ b/README.md @@ -34,7 +34,7 @@ NAGI STUDIO 的 LLM 测评案例集：同一段提示词，不同「模型 × Ha | Claude Opus 4.7 | Anthropic | Cursor · Max | 02 | | Claude Opus 4.6 | Anthropic | Cursor · Max | 02 | | Claude Opus 4.5 | Anthropic | Cursor · Thinking | 02 | -| Claude Sonnet 4.6 | Anthropic | Cursor · High | 01 | +| Claude Sonnet 4.6 | Anthropic | Claude Code · Max
Cursor · High | 03 | | GPT-5.5 Pro | OpenAI | ChatGPT Web · Extended Pro | 02 | | GPT-5.5 | OpenAI | Codex CLI · xhigh | 02 | | GPT-5.4 | OpenAI | Cursor · xhigh
Codex CLI · xhigh | 05 | diff --git a/models/claude-sonnet-4-6-cc.json b/models/claude-sonnet-4-6-cc.json new file mode 100644 index 0000000..d52999e --- /dev/null +++ b/models/claude-sonnet-4-6-cc.json @@ -0,0 +1,18 @@ +{ + "label": "Claude Sonnet 4.6", + "vendor": "Anthropic", + "harness": "Claude Code", + "effort": "Max", + "artifactDir": "claude-sonnet-4-6/claude-code-max", + "order": 18.9, + "runs": { + "pelican-cycling": { + "file": "pelican-beach.svg", + "note": { + "zh": "在 Claude Code 中以 Claude Sonnet 4.6（Max 思考配额）一次生成。", + "en": "Generated in one shot by Claude Sonnet 4.6 (Max effort) inside Claude Code." + }, + "contributor": "Nagi-ovo" + } + } +} diff --git a/models/claude-sonnet-4-6-cursor.json b/models/claude-sonnet-4-6-cursor.json index 2847eac..72fdedb 100644 --- a/models/claude-sonnet-4-6-cursor.json +++ b/models/claude-sonnet-4-6-cursor.json @@ -6,13 +6,23 @@ "artifactDir": "claude-sonnet-4-6/cursor-high", "order": 19, "runs": { - "pelican-cycling": { - "file": "pelican-beach.svg", - "note": { - "zh": "在 Cursor CLI 中以 Claude Sonnet 4.6（High 思考配额）一次生成。原始 SVG 的注释中混入非法 XML/编码字节，导致浏览器只渲染到一半并显示解析错误；Codex 仅将这些注释里的坏字符替换为 ASCII 连字符以修复加载错误，未改动任何图形元素。", - "en": "Generated in one shot by Claude Sonnet 4.6 (High effort) inside Cursor CLI. The original SVG contained invalid XML/encoding bytes inside comments, causing browsers to stop rendering partway through with a parse error; Codex only replaced those bad comment characters with ASCII hyphens to fix loading, without changing any graphical elements." + "pelican-cycling": [ + { + "file": "pelican-beach.svg", + "note": { + "zh": "在 Cursor CLI 中以 Claude Sonnet 4.6（High 思考配额）一次生成。原始 SVG 的注释中混入非法 XML/编码字节，导致浏览器只渲染到一半并显示解析错误；Codex 仅将这些注释里的坏字符替换为 ASCII 连字符以修复加载错误，未改动任何图形元素。", + "en": "Generated in one shot by Claude Sonnet 4.6 (High effort) inside Cursor CLI. The original SVG contained invalid XML/encoding bytes inside comments, causing browsers to stop rendering partway through with a parse error; Codex only replaced those bad comment characters with ASCII hyphens to fix loading, without changing any graphical elements." + }, + "contributor": "Nagi-ovo" }, - "contributor": "Nagi-ovo" - } + { + "file": "pelican-beach-2.svg", + "note": { + "zh": "第二版：在 Cursor CLI 中以 Claude Sonnet 4.6（High 思考配额）一次生成，作为独立 SVG 变体登记，保留原版产物不变。", + "en": "Second version: generated in one shot by Claude Sonnet 4.6 (High effort) inside Cursor CLI and registered as a separate SVG variant, preserving the original artifact." + }, + "contributor": "Nagi-ovo" + } + ] } } diff --git a/outputs/claude-sonnet-4-6/claude-code-max/pelican-beach.svg b/outputs/claude-sonnet-4-6/claude-code-max/pelican-beach.svg new file mode 100644 index 0000000..176d244 --- /dev/null +++ b/outputs/claude-sonnet-4-6/claude-code-max/pelican-beach.svg @@ -0,0 +1,416 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/outputs/claude-sonnet-4-6/cursor-high/pelican-beach-2.svg b/outputs/claude-sonnet-4-6/cursor-high/pelican-beach-2.svg new file mode 100644 index 0000000..ef94559 --- /dev/null +++ b/outputs/claude-sonnet-4-6/cursor-high/pelican-beach-2.svg @@ -0,0 +1,561 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +