diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md new file mode 100644 index 0000000..32dd6e3 --- /dev/null +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -0,0 +1,18 @@ + + + +## 产出说明 / Run info + +- 模型 / Model: +- 运行环境 / Harness(如 ChatGPT Web、Claude Code、Google AI Studio、本地 CLI…): +- 思考配额 / Thinking effort(如 Max、High、Extended Pro、Thinking…): +- 是否一次生成 / One-shot? (是/否;若有修复请在 note 里说明 / if fixed, document it in the note) + +## 自查 / Checklist + +- [ ] `models/.json` 中 `harness` 与 `effort` 已如实填写(站点据此生成 metadata 与品牌 icon) +- [ ] 每条 run 的 `note` 双语(zh + en)填写了上面的来历信息 / bilingual `note` documents the provenance above +- [ ] `contributor` 是我的 GitHub 用户名 / `contributor` is my GitHub username +- [ ] 同一模型在不同 Harness 或思考配额下是**新建一个 JSON 条目**,不是塞进现有条目 / a different harness or effort = a NEW json entry, not a variant + + diff --git a/README.en.md b/README.en.md index de64787..0a261d1 100644 --- a/README.en.md +++ b/README.en.md @@ -20,15 +20,17 @@ One-shot LLM eval cases by NAGI STUDIO: same prompt, different model x harness x | Claude Fable 5 | Anthropic | Claude Code | Max | 02 | | 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 | 03 | -| Gemini 3.5 Flash | Google | AntiGravity | High | 03 | +| Gemini 3.1 Pro | Google | AntiGravity | High | 02 | +| Gemini 3.1 Pro | Google | Google AI Studio | High | 01 | +| Gemini 3.5 Flash | Google | AntiGravity | High | 02 | +| Gemini 3.5 Flash | Google | Google AI Studio | High | 01 | | Grok Build | xAI | Grok Build TUI (local) | Max | 02 | | Composer 2.5 | Cursor | Cursor | Max | 01 | | DeepSeek-V4-Pro | DeepSeek | Claude Code | Max | 02 | | Doubao Seed 2.0 Pro | ByteDance | Doubao Web | Pro Mode | 01 | | Doubao Seed 2.0 Mini | ByteDance | Doubao Web | Fast Mode | 01 | | MiMo v2.5 Pro | Xiaomi | Claude Code | Max | 02 | -| Kimi K2.6 | Moonshot AI | Kimi Code (local) | Default | 01 | +| Kimi K2.6 | Moonshot AI | Kimi Code (local) | Default | 02 | | MiniMax M3 | MiniMax | MiniMax Code Web | Thinking | 01 | Pending: Mistral Medium 3.5 · GLM-5.1 · Qwen3.7-Max (PRs welcome) diff --git a/README.md b/README.md index 52c5374..f55dce3 100644 --- a/README.md +++ b/README.md @@ -20,15 +20,17 @@ 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 Code | Max | 02 | | 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 | 03 | -| Gemini 3.5 Flash | Google | AntiGravity | High | 03 | +| Gemini 3.1 Pro | Google | AntiGravity | High | 02 | +| Gemini 3.1 Pro | Google | Google AI Studio | High | 01 | +| Gemini 3.5 Flash | Google | AntiGravity | High | 02 | +| Gemini 3.5 Flash | Google | Google AI Studio | High | 01 | | Grok Build | xAI | Grok Build TUI(本地) | Max | 02 | | Composer 2.5 | Cursor | Cursor | Max | 01 | | DeepSeek-V4-Pro | DeepSeek | Claude Code | Max | 02 | | Doubao Seed 2.0 Pro | ByteDance | 豆包网页版 | 超能模式 | 01 | | Doubao Seed 2.0 Mini | ByteDance | 豆包网页版 | 快速模式 | 01 | | MiMo v2.5 Pro | Xiaomi | Claude Code | Max | 02 | -| Kimi K2.6 | Moonshot AI | Kimi Code(本地) | Default | 01 | +| Kimi K2.6 | Moonshot AI | Kimi Code(本地) | Default | 02 | | MiniMax M3 | MiniMax | MiniMax Code 网页版 | Thinking | 01 | 待测:Mistral Medium 3.5 · GLM-5.1 · Qwen3.7-Max(欢迎 PR 补充) diff --git a/models/gemini-3-1-pro-aistudio.json b/models/gemini-3-1-pro-aistudio.json new file mode 100644 index 0000000..33a3e78 --- /dev/null +++ b/models/gemini-3-1-pro-aistudio.json @@ -0,0 +1,16 @@ +{ + "label": "Gemini 3.1 Pro", + "vendor": "Google", + "harness": "Google AI Studio", + "effort": "High", + "order": 42, + "runs": { + "pelican-cycling": { + "note": { + "zh": "在 Google AI Studio 以 Gemini 3.1 Pro Preview High(最高思考强度)一次生成。", + "en": "Generated in Google AI Studio on Gemini 3.1 Pro Preview High (max thinking effort) in one shot." + }, + "contributor": "LpIuma" + } + } +} diff --git a/models/gemini-3-1-pro.json b/models/gemini-3-1-pro.json index 65566b7..c891628 100644 --- a/models/gemini-3-1-pro.json +++ b/models/gemini-3-1-pro.json @@ -12,22 +12,13 @@ }, "contributor": "Nagi-ovo" }, - "pelican-cycling": [ - { - "note": { - "zh": "在 Google AI Studio 以 Gemini 3.1 Pro Preview High(最高思考强度)一次生成。", - "en": "Generated in Google AI Studio on Gemini 3.1 Pro Preview High (max thinking effort) in one shot." - }, - "contributor": "LpIuma" + "pelican-cycling": { + "file": "pelican-cycling-2.svg", + "note": { + "zh": "由社区 PR #3(Codex 工作流)提交,提交者未注明运行环境与思考档位。", + "en": "Contributed via community PR #3 (a Codex workflow); the submitter did not specify the runtime or effort level." }, - { - "file": "pelican-cycling-2.svg", - "note": { - "zh": "由社区 PR #3(Codex 工作流)提交,提交者未注明运行环境与思考档位。", - "en": "Contributed via community PR #3 (a Codex workflow); the submitter did not specify the runtime or effort level." - }, - "contributor": "XA2333" - } - ] + "contributor": "XA2333" + } } } diff --git a/models/gemini-3-5-flash-aistudio.json b/models/gemini-3-5-flash-aistudio.json new file mode 100644 index 0000000..31af949 --- /dev/null +++ b/models/gemini-3-5-flash-aistudio.json @@ -0,0 +1,16 @@ +{ + "label": "Gemini 3.5 Flash", + "vendor": "Google", + "harness": "Google AI Studio", + "effort": "High", + "order": 52, + "runs": { + "pelican-cycling": { + "note": { + "zh": "在 Google AI Studio 以 Gemini 3.5 Flash High(最高思考强度)一次生成。", + "en": "Generated in Google AI Studio on Gemini 3.5 Flash High (max thinking effort) in one shot." + }, + "contributor": "LpIuma" + } + } +} diff --git a/models/gemini-3-5-flash.json b/models/gemini-3-5-flash.json index e1e21e9..934fff2 100644 --- a/models/gemini-3-5-flash.json +++ b/models/gemini-3-5-flash.json @@ -12,22 +12,13 @@ }, "contributor": "Nagi-ovo" }, - "pelican-cycling": [ - { - "note": { - "zh": "在 Google AI Studio 以 Gemini 3.5 Flash High(最高思考强度)一次生成。", - "en": "Generated in Google AI Studio on Gemini 3.5 Flash High (max thinking effort) in one shot." - }, - "contributor": "LpIuma" + "pelican-cycling": { + "file": "pelican-cycling-2.svg", + "note": { + "zh": "由社区 PR #3(Codex 工作流)提交,提交者未注明运行环境与思考档位。", + "en": "Contributed via community PR #3 (a Codex workflow); the submitter did not specify the runtime or effort level." }, - { - "file": "pelican-cycling-2.svg", - "note": { - "zh": "由社区 PR #3(Codex 工作流)提交,提交者未注明运行环境与思考档位。", - "en": "Contributed via community PR #3 (a Codex workflow); the submitter did not specify the runtime or effort level." - }, - "contributor": "XA2333" - } - ] + "contributor": "XA2333" + } } } diff --git a/models/kimi-k2-6.json b/models/kimi-k2-6.json index 5ed4765..b02cd48 100644 --- a/models/kimi-k2-6.json +++ b/models/kimi-k2-6.json @@ -5,6 +5,13 @@ "harness": "Kimi Code", "effort": "Default", "runs": { + "mythos-craft": { + "note": { + "zh": "在本地以 Kimi Code(harness)运行 Kimi K2.6 一次生成,本页为未经修改的原始产出。", + "en": "Generated in one shot by Kimi K2.6 running locally in Kimi Code; unmodified original output." + }, + "contributor": "Nagi-ovo" + }, "pelican-cycling": { "note": { "zh": "在本地以 Kimi Code(harness)运行 Kimi K2.6 一次生成。", diff --git a/outputs/gemini-3-1-pro/pelican-cycling.svg b/outputs/gemini-3-1-pro-aistudio/pelican-cycling.svg similarity index 100% rename from outputs/gemini-3-1-pro/pelican-cycling.svg rename to outputs/gemini-3-1-pro-aistudio/pelican-cycling.svg diff --git a/outputs/gemini-3-5-flash/pelican-cycling.svg b/outputs/gemini-3-5-flash-aistudio/pelican-cycling.svg similarity index 100% rename from outputs/gemini-3-5-flash/pelican-cycling.svg rename to outputs/gemini-3-5-flash-aistudio/pelican-cycling.svg diff --git a/outputs/kimi-k2-6/mythos-craft.html b/outputs/kimi-k2-6/mythos-craft.html new file mode 100644 index 0000000..633372b --- /dev/null +++ b/outputs/kimi-k2-6/mythos-craft.html @@ -0,0 +1,1608 @@ + + + + + + 神话世界 - MythicWorld + + + + +
+

神话世界

+
MythicWorld - 无限创造的幻想沙盒
+
+
正在初始化世界...
+
+ +
+

神话世界

+

点击屏幕进入游戏,使用鼠标环视四周

+

WASD 移动 | 空格 跳跃 | Shift 潜行

+

鼠标左键 破坏方块 | 鼠标右键 放置方块

+

数字键 1-9 切换方块类型

+ +
+ +
+
+
+
位置: 0, 0, 0
+
朝向: 0
+
方块: 无
+
+
按 ESC 暂停 | 左键破坏 | 右键放置
+
+ + + +