diff --git a/README.en.md b/README.en.md index cc3f4fa..de64787 100644 --- a/README.en.md +++ b/README.en.md @@ -17,19 +17,21 @@ One-shot LLM eval cases by NAGI STUDIO: same prompt, different model x harness x | Model | Vendor | Harness | Effort | Runs | |---|---|---|---|---| | Claude Fable 5 | Anthropic | Claude Web App | Max | 02 | -| Claude Fable 5 | Anthropic | Claude Code | Max | 01 | +| 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 | -| Grok Build | xAI | Grok Build TUI (local) | Max | 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 | +| MiniMax M3 | MiniMax | MiniMax Code Web | Thinking | 01 | -Pending: Mistral Medium 3.5 · Kimi K2.6 · MiniMax M3 · 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 b549752..52c5374 100644 --- a/README.md +++ b/README.md @@ -17,19 +17,21 @@ NAGI STUDIO 的 LLM 测评案例集：同一段提示词，不同「模型 × Ha | 模型 | 厂商 | Harness 环境 | 思考配额 | 产出 | |---|---|---|---|---| | Claude Fable 5 | Anthropic | Claude 网页版 | Max | 02 | -| Claude Fable 5 | Anthropic | Claude Code | Max | 01 | +| 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 | -| Grok Build | xAI | Grok Build TUI（本地） | Max | 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 | +| MiniMax M3 | MiniMax | MiniMax Code 网页版 | Thinking | 01 | -待测：Mistral Medium 3.5 · Kimi K2.6 · MiniMax M3 · 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-fable-5-code.json b/models/claude-fable-5-code.json index 1288397..74ef28d 100644 --- a/models/claude-fable-5-code.json +++ b/models/claude-fable-5-code.json @@ -11,6 +11,13 @@ "en": "Generated in one shot by Claude Fable 5 (Max effort) inside Claude Code; this page is the unmodified original output. Same model as the Claude Web App entry but a different harness — compare the two tabs to see how the environment shapes the result." }, "contributor": "Nagi-ovo" + }, + "pelican-cycling": { + "note": { + "zh": "在 Claude Code 中以 Claude Fable 5（Max 思考配额）一次生成。", + "en": "Generated in one shot by Claude Fable 5 (Max effort) inside Claude Code." + }, + "contributor": "Nagi-ovo" } } } diff --git a/models/grok-build.json b/models/grok-build.json index d3b5ff0..84ba41a 100644 --- a/models/grok-build.json +++ b/models/grok-build.json @@ -11,6 +11,13 @@ "en": "Built locally with the Grok Build TUI; fixed build (3 lines changed). Bug 1: line 82 const WORLD_SEED = 0xAETHER — T/H/R are not hex digits, so the whole script threw a SyntaxError at parse time; before the fix the screen was pure black with only HTML text. Bug 2: the atlas is drawn in the top canvas rows with top-left-origin UVs but no flipY=false, so every face sampled the undrawn black region; before the fix nearby terrain rendered solid black. Bug 3: the forward vector already points where the camera looks, but W subtracted and S added — W walked backward (A/D were fine). One line each; everything else is Grok as-is." }, "contributor": "Nagi-ovo" + }, + "pelican-cycling": { + "note": { + "zh": "在本地通过 Grok Build（TUI）一次生成。", + "en": "Generated in one shot locally via the Grok Build TUI." + }, + "contributor": "Nagi-ovo" } } } diff --git a/models/kimi-k2-6.json b/models/kimi-k2-6.json index bd522fe..5ed4765 100644 --- a/models/kimi-k2-6.json +++ b/models/kimi-k2-6.json @@ -1,5 +1,16 @@ { "label": "Kimi K2.6", "vendor": "Moonshot AI", - "order": 100 + "order": 100, + "harness": "Kimi Code", + "effort": "Default", + "runs": { + "pelican-cycling": { + "note": { + "zh": "在本地以 Kimi Code（harness）运行 Kimi K2.6 一次生成。", + "en": "Generated in one shot by Kimi K2.6 running locally in Kimi Code." + }, + "contributor": "Nagi-ovo" + } + } } diff --git a/models/minimax-m3.json b/models/minimax-m3.json index d48f4ac..6c93e9e 100644 --- a/models/minimax-m3.json +++ b/models/minimax-m3.json @@ -1,5 +1,16 @@ { "label": "MiniMax M3", "vendor": "MiniMax", - "order": 110 + "order": 110, + "harness": "MiniMax Code Web", + "effort": "Thinking", + "runs": { + "pelican-cycling": { + "note": { + "zh": "在 MiniMax Code 网页版以 MiniMax M3（开启思考模式 Thinking）一次生成。", + "en": "Generated in one shot by MiniMax M3 (Thinking mode on) in the MiniMax Code web app." + }, + "contributor": "Nagi-ovo" + } + } } diff --git a/outputs/claude-fable-5-code/pelican-cycling.svg b/outputs/claude-fable-5-code/pelican-cycling.svg new file mode 100644 index 0000000..ee3840b --- /dev/null +++ b/outputs/claude-fable-5-code/pelican-cycling.svg @@ -0,0 +1,370 @@ + + 海边骑行的鹈鹕 · A pelican riding a bicycle by the sea + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/outputs/grok-build/pelican-cycling.svg b/outputs/grok-build/pelican-cycling.svg new file mode 100644 index 0000000..abdbbba --- /dev/null +++ b/outputs/grok-build/pelican-cycling.svg @@ -0,0 +1,568 @@ + + Seaside Pelican on a Bicycle + A realistic and vivid pelican riding a bicycle along a sunny beach with turquoise waves, golden sand, and blue sky. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/outputs/kimi-k2-6/pelican-cycling.svg b/outputs/kimi-k2-6/pelican-cycling.svg new file mode 100644 index 0000000..1cb67e2 --- /dev/null +++ b/outputs/kimi-k2-6/pelican-cycling.svg @@ -0,0 +1,404 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/outputs/minimax-m3/pelican-cycling.svg b/outputs/minimax-m3/pelican-cycling.svg new file mode 100644 index 0000000..924aae8 --- /dev/null +++ b/outputs/minimax-m3/pelican-cycling.svg @@ -0,0 +1,460 @@ + + + Pelican Biking by the Sea + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +