diff --git a/README.en.md b/README.en.md index e9f26fb..033a6cf 100644 --- a/README.en.md +++ b/README.en.md @@ -42,23 +42,23 @@ One-shot LLM eval cases by NAGI STUDIO: same prompt, different model x harness x | GPT-5.4 | OpenAI | Cursor · xhigh
Codex CLI · xhigh | 05 | | GPT-5.3 Codex | OpenAI | Cursor · xhigh | 02 | | GPT-5.2 | OpenAI | Cursor · xhigh | 02 | -| Gemini 3.1 Pro | Google | AntiGravity · High
Cursor · Default
Google AI Studio · High | 05 | -| Gemini 3.5 Flash | Google | AntiGravity · High
Cursor · Default
Google AI Studio · High | 05 | +| Gemini 3.1 Pro | Google | AntiGravity · High
Cursor · Default
Google AI Studio · High | 06 | +| Gemini 3.5 Flash | Google | AntiGravity · High
Cursor · Default
Google AI Studio · High | 06 | | Grok Build | xAI | Grok Build TUI · Max | 02 | | Nex-N2-Pro | Nex-AGI | Claude Code · Max | 02 | | Grok 4.3 | xAI | Cursor · Default | 02 | | Composer 2.5 | Cursor | Cursor · Max
Cursor · Default
Grok Build TUI · Default | 05 | | Mistral Medium 3.5 | Mistral AI | Vibe · Thinking | 02 | -| DeepSeek-V4-Pro | DeepSeek | Claude Code · Max | 02 | +| DeepSeek-V4-Pro | DeepSeek | Claude Code · Max | 03 | | 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 | -| MiMo v2.5 Pro UltraSpeed | Xiaomi | Web · Default | 04 | -| Kimi K2.7-Code | Moonshot AI | Kimi Code · Thinking | 02 | +| MiMo v2.5 Pro | Xiaomi | Claude Code · Max
MiMo Code · Max | 03 | +| MiMo v2.5 Pro UltraSpeed | Xiaomi | Web · Default | 05 | +| Kimi K2.7-Code | Moonshot AI | Kimi Code · Thinking | 03 | | Kimi K2.6 | Moonshot AI | Kimi Code · Thinking | 02 | | MiniMax M3 | MiniMax | MiniMax Code Web · Thinking | 02 | | MiniMax M2.7 | MiniMax | MiniMax Code Web · Thinking | 01 | -| GLM-5.2 | Zhipu AI | ZCode · Max | 03 | +| GLM-5.2 | Zhipu AI | ZCode · Max | 04 | | GLM-5 Turbo | Zhipu AI | ZCode · Thinking | 03 | | Qwen3.7-Max | Alibaba | Qoder · Default | 02 | | Step 3.7 Flash | StepFun | Claude Code · High | 02 | diff --git a/README.md b/README.md index 35432b4..ae744f4 100644 --- a/README.md +++ b/README.md @@ -42,23 +42,23 @@ NAGI STUDIO 的 LLM 测评案例集:同一段提示词,不同「模型 × Ha | GPT-5.4 | OpenAI | Cursor · xhigh
Codex CLI · xhigh | 05 | | GPT-5.3 Codex | OpenAI | Cursor · xhigh | 02 | | GPT-5.2 | OpenAI | Cursor · xhigh | 02 | -| Gemini 3.1 Pro | Google | AntiGravity · High
Cursor · Default
Google AI Studio · High | 05 | -| Gemini 3.5 Flash | Google | AntiGravity · High
Cursor · Default
Google AI Studio · High | 05 | +| Gemini 3.1 Pro | Google | AntiGravity · High
Cursor · Default
Google AI Studio · High | 06 | +| Gemini 3.5 Flash | Google | AntiGravity · High
Cursor · Default
Google AI Studio · High | 06 | | Grok Build | xAI | Grok Build TUI · Max | 02 | | Nex-N2-Pro | Nex-AGI | Claude Code · Max | 02 | | Grok 4.3 | xAI | Cursor · Default | 02 | | Composer 2.5 | Cursor | Cursor · Max
Cursor · Default
Grok Build TUI · Default | 05 | | Mistral Medium 3.5 | Mistral AI | Vibe · Thinking | 02 | -| DeepSeek-V4-Pro | DeepSeek | Claude Code · Max | 02 | +| DeepSeek-V4-Pro | DeepSeek | Claude Code · Max | 03 | | 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 | -| MiMo v2.5 Pro UltraSpeed | Xiaomi | Web · Default | 04 | -| Kimi K2.7-Code | Moonshot AI | Kimi Code · Thinking | 02 | +| MiMo v2.5 Pro | Xiaomi | Claude Code · Max
MiMo Code · Max | 03 | +| MiMo v2.5 Pro UltraSpeed | Xiaomi | Web · Default | 05 | +| Kimi K2.7-Code | Moonshot AI | Kimi Code · Thinking | 03 | | Kimi K2.6 | Moonshot AI | Kimi Code · Thinking | 02 | | MiniMax M3 | MiniMax | MiniMax Code Web · Thinking | 02 | | MiniMax M2.7 | MiniMax | MiniMax Code Web · Thinking | 01 | -| GLM-5.2 | Zhipu AI | ZCode · Max | 03 | +| GLM-5.2 | Zhipu AI | ZCode · Max | 04 | | GLM-5 Turbo | Zhipu AI | ZCode · Thinking | 03 | | Qwen3.7-Max | Alibaba | Qoder · Default | 02 | | Step 3.7 Flash | StepFun | Claude Code · High | 02 | diff --git a/models/deepseek-v4-pro.json b/models/deepseek-v4-pro.json index 0b20c11..f244453 100644 --- a/models/deepseek-v4-pro.json +++ b/models/deepseek-v4-pro.json @@ -19,6 +19,13 @@ "en": "Generated in one shot via Claude Code with DeepSeek V4 Pro (max thinking effort). Scene includes sky, ocean, beach, palm trees, seagulls, detailed bicycle (spokes, chain, gears), and a pelican (beak, gular pouch, wings, pedaling pose)." }, "contributor": "Mintcolour" + }, + "skeleton-watch": { + "note": { + "zh": "在 Claude Code 中以 DeepSeek-V4-Pro(最高思考强度)一次生成,未进行任何修改。", + "en": "Generated in one shot by DeepSeek-V4-Pro inside Claude Code with Max effort, unmodified." + }, + "contributor": "OHCJ099" } } } diff --git a/models/gemini-3-1-pro.json b/models/gemini-3-1-pro.json index e6a367e..f62aa63 100644 --- a/models/gemini-3-1-pro.json +++ b/models/gemini-3-1-pro.json @@ -20,6 +20,13 @@ "en": "Contributed via community PR #3 (a Codex workflow); the submitter did not specify the runtime or effort level." }, "contributor": "XA2333" + }, + "skeleton-watch": { + "note": { + "zh": "通过 AntiGravity 生成(thinking effort: high);一次生成,未进行任何修改。", + "en": "Generated via AntiGravity (thinking effort: high); one shot, unmodified." + }, + "contributor": "OHCJ099" } } } diff --git a/models/gemini-3-5-flash.json b/models/gemini-3-5-flash.json index 3a0fdf9..cd52e8c 100644 --- a/models/gemini-3-5-flash.json +++ b/models/gemini-3-5-flash.json @@ -20,6 +20,13 @@ "en": "Contributed via community PR #3 (a Codex workflow); the submitter did not specify the runtime or effort level." }, "contributor": "XA2333" + }, + "skeleton-watch": { + "note": { + "zh": "通过 AntiGravity 生成(thinking effort: high);一次生成,未进行任何修改。", + "en": "Generated via AntiGravity (thinking effort: high); one shot, unmodified." + }, + "contributor": "OHCJ099" } } } diff --git a/models/glm-5-2.json b/models/glm-5-2.json index 4349192..3c05a55 100644 --- a/models/glm-5-2.json +++ b/models/glm-5-2.json @@ -29,6 +29,13 @@ }, "contributor": "Nagi-ovo" } - ] + ], + "skeleton-watch": { + "note": { + "zh": "在 ZCode 中以 GLM-5.2(Max 思考配额)一次生成,未进行任何修改。", + "en": "Generated in one shot by GLM-5.2 (Max effort) inside ZCode, unmodified." + }, + "contributor": "OHCJ099" + } } } diff --git a/models/kimi-k2-7-code.json b/models/kimi-k2-7-code.json index df3bdb6..fbd31a3 100644 --- a/models/kimi-k2-7-code.json +++ b/models/kimi-k2-7-code.json @@ -19,6 +19,13 @@ "en": "Generated in one shot by Kimi K2.7-Code running in Kimi Code with Thinking mode." }, "contributor": "OHCJ099" + }, + "skeleton-watch": { + "note": { + "zh": "在 Kimi Code 中使用 Kimi K2.7-Code 模型(Thinking 档位)一次生成,未进行任何修改。", + "en": "Generated in one shot by Kimi K2.7-Code running in Kimi Code with Thinking mode, unmodified." + }, + "contributor": "OHCJ099" } } } diff --git a/models/mimo-v2-5-pro-mimocode.json b/models/mimo-v2-5-pro-mimocode.json new file mode 100644 index 0000000..b6adb29 --- /dev/null +++ b/models/mimo-v2-5-pro-mimocode.json @@ -0,0 +1,16 @@ +{ + "label": "MiMo v2.5 Pro", + "vendor": "Xiaomi", + "harness": "MiMo Code", + "effort": "Max", + "order": 97.2, + "runs": { + "skeleton-watch": { + "note": { + "zh": "在 MiMo Code 中使用 MiMo v2.5 Pro 模型一次生成,未进行任何修改。", + "en": "Generated in one shot by MiMo v2.5 Pro in MiMo Code, unmodified." + }, + "contributor": "OHCJ099" + } + } +} diff --git a/models/mimo-v2-5-pro-ultraspeed.json b/models/mimo-v2-5-pro-ultraspeed.json index 154bf3c..4871369 100644 --- a/models/mimo-v2-5-pro-ultraspeed.json +++ b/models/mimo-v2-5-pro-ultraspeed.json @@ -38,6 +38,13 @@ "file": "pelican-cycling-2.svg", "contributor": "OHCJ099" } - ] + ], + "skeleton-watch": { + "note": { + "zh": "在 Web 环境中使用 MiMo v2.5 Pro UltraSpeed 一次生成,未做任何修改。", + "en": "Generated in one shot by MiMo v2.5 Pro UltraSpeed in Web environment, with no modifications." + }, + "contributor": "OHCJ099" + } } } diff --git a/outputs/deepseek-v4-pro/claude-code-max/skeleton-watch.html b/outputs/deepseek-v4-pro/claude-code-max/skeleton-watch.html new file mode 100644 index 0000000..f0ac0c1 --- /dev/null +++ b/outputs/deepseek-v4-pro/claude-code-max/skeleton-watch.html @@ -0,0 +1,1597 @@ + + + + + +3D 镂空机械腕表 + + + + +
+
+ +
+
+ Calibre Squelette + Tourbillon · Manufacture +
+
+ +
+ +
+

组件详情

+
+
+
+
+ +
+ + + + +
+ + + + + + diff --git a/outputs/gemini-3-1-pro/antigravity-high/skeleton-watch.html b/outputs/gemini-3-1-pro/antigravity-high/skeleton-watch.html new file mode 100644 index 0000000..848080e --- /dev/null +++ b/outputs/gemini-3-1-pro/antigravity-high/skeleton-watch.html @@ -0,0 +1,595 @@ + + + + + + Aero Tourbillon - 3D Skeleton Watch + + + +
+
+
ASSEMBLING MOVEMENT...
+
+ +
+ +
+
+

AEROTOURBILLON

+

CALIBER X-01 SKELETON

+
+ +
+ + +
+ +
+

Component

+

Description goes here.

+
+ +
Tooltip
+
+ + + + + + + diff --git a/outputs/gemini-3-5-flash/antigravity-high/skeleton-watch.html b/outputs/gemini-3-5-flash/antigravity-high/skeleton-watch.html new file mode 100644 index 0000000..06048a5 --- /dev/null +++ b/outputs/gemini-3-5-flash/antigravity-high/skeleton-watch.html @@ -0,0 +1,2108 @@ + + + + + + Haute Horlogerie - 3D 镂空机械表 + + + + + + + + + + + + +
+
+
HAUTE HORLOGERIE
+
正在组装 3D 机械核心...
+
+
+

HAUTE HORLOGERIE

+

为了获得最佳奢华体验,请在桌面端或更宽的屏幕上浏览此 3D 机械表模型。

+ +
+
+
+
零件名称
+
+ +
+
+ CALIBRE . S1 + 镂空飞轮机械机芯 +
+
+ + 振频: 4.0 Hz / 28800 vph +
+
+ + + + + + + + +
+ + + + \ No newline at end of file diff --git a/outputs/glm-5-2/zcode-max/skeleton-watch.html b/outputs/glm-5-2/zcode-max/skeleton-watch.html new file mode 100644 index 0000000..dfe9063 --- /dev/null +++ b/outputs/glm-5-2/zcode-max/skeleton-watch.html @@ -0,0 +1,1088 @@ + + + + + +SKELETON — 镂空机械腕表 3D 展示 + + + +
+ +
+
+
MANUFACTURE · GENÈVE
+
SKELETON
+
CAL. T-9128 · TOURBILLON STYLE
+
+
+
RÉFÉRENCE
+
N°0247 / 250
+
+
+ +
+

CONTRÔLES

+
自动旋转
+
机芯运转
+
背景反射
+
辉光 (Bloom)
+
摆轮速率5.0 Hz
+ + +
+ 鼠标拖拽旋转 · 滚轮缩放
+ 悬停零件查看名称 · 点击展开详情 +
+
+ + + +
+
00:00:00
+
SYNCHRONIZED · LOCAL TIME
+
+ +
CALIBRATING MOVEMENT…
+ + + + + + diff --git a/outputs/kimi-k2-7-code/kimi-code-thinking/skeleton-watch.html b/outputs/kimi-k2-7-code/kimi-code-thinking/skeleton-watch.html new file mode 100644 index 0000000..eb071e4 --- /dev/null +++ b/outputs/kimi-k2-7-code/kimi-code-thinking/skeleton-watch.html @@ -0,0 +1,1023 @@ + + + + + + 镂空机械表 · 3D 交互展示 + + + +
ASSEMBLING MOVEMENT…
+
+ +
+

Skeleton Tourbillon

+

镂空机械机芯 · 实时交互展示

+
+ +
+ 拖拽旋转 · 滚轮缩放 · 悬停查看零件 · 点击显示详情 +
+ +
+ + + + +
+ +
+ +
⚙️
+

零件名称

+
COMPONENT
+

点击零件查看详细说明。

+
+ +
零件
+
+ + + + + diff --git a/outputs/mimo-v2-5-pro-mimocode/skeleton-watch.html b/outputs/mimo-v2-5-pro-mimocode/skeleton-watch.html new file mode 100644 index 0000000..ba1a3ad --- /dev/null +++ b/outputs/mimo-v2-5-pro-mimocode/skeleton-watch.html @@ -0,0 +1,1090 @@ + + + + + +3D Skeleton Watch + + + +
+

Skeleton

Haute Horlogerie · Interactive 3D

+
+

Movement Details

+
CaliberSK-2024A
+
TypeManual Wind
+
Frequency28,800 vph
+
Jewels21 Rubies
+
Power Reserve72 Hours
+
Diameter39mm
+
Thickness8.5mm
+
FinishHand Angled
+
Case18K Rose Gold
+
CrystalSapphire
+ +
+
+
Movement Architecture
+Main Plate: German Silver
+Bridges: Hand-finished, Beveled
+Gear Train: 4 Wheels
+Escapement: Swiss Lever
+Balance: Glucydur
+Hairspring: Nivarox
+Oscillation: 4 Hz +
+
+
+ + + + +
+ + + + + diff --git a/outputs/mimo-v2-5-pro-ultraspeed/skeleton-watch.html b/outputs/mimo-v2-5-pro-ultraspeed/skeleton-watch.html new file mode 100644 index 0000000..00b7a61 --- /dev/null +++ b/outputs/mimo-v2-5-pro-ultraspeed/skeleton-watch.html @@ -0,0 +1,456 @@ + + + + + +Calibre · Skeleton Haute Horlogerie + + + + + +
Calibrating
+
+

Calibre

Skeleton Collection — Ref. 7721

+
41mm · 18K Rose Gold
Hand-Wound · 72h Power Reserve
28,800 vph · 21 Jewels
+
+
+ + + +
+

Component

+
+ + + + + \ No newline at end of file