● onlinetty/0guest@bubucn:~$
v0.7.2utc+08static
05 · ai_model_evals

Water Shader
AI 模型横评。

同一组 prompt。截图优先。HTML 全部可打开。

Contact sheet of all real water shader benchmark screenshots28 张截图 · 10 条路线 · HTML 可打开
正在体验

Claude Opus 4.7 Adaptive

final · Microfacet water pass

02 · 投票

模型favourites

给你真想转发的产出投一票。

03 · prompt 与执行日志

prompt 与执行链

需要原始 prompt 时再展开。

P0原始评测 promptbase

每个模型都拿这一条,全新会话、无 system prompt。

Create an ultra-realistic 3D ocean / water simulation system and deliver it as a single self-contained HTML file.

The goal is to stress-test advanced AI capability in real-time 3D graphics, GLSL shader programming, physically inspired water simulation, interactive parameter control, and floating object physics.

Core Requirement:
- Build a real-time 3D water scene, not a 2D canvas ripple effect.
- The final output must be a single complete `.html` file.
- The file must run directly in a modern browser.
- Use WebGL, GLSL shaders, and/or Three.js.
- If Three.js is used, it must be loaded from a CDN inside the HTML file.
- Do not use external image assets, model files, texture files, or build tools.
- All geometry, materials, shaders, boats, sky, UI, and effects must be generated procedurally or inline.

Rendering Requirements:
- Implement a 3D water surface using a high-resolution plane mesh or procedural geometry.
- The water must use custom shader logic or shader-like material behavior.
- Include realistic water effects such as vertex displacement, multi-layer sine/Gerstner waves, wind-driven direction, dynamic amplitude, wave speed controls, surface normal calculation, specular highlights, Fresnel reflection, environment reflection approximation, depth-based water color, foam or whitecaps on steep waves, sun/light controls, and a sky gradient or procedural environment.
- The water surface must visibly behave like a 3D ocean/lake, not a flat animated texture.
P1首屏没水修复no-water repair

水没出来时用:GPT-5.5 Pro Extended Thinking、GPT-5.5 Standard、GLM-5.1。

i could not see the water.
P2泛质量提升quality

已经有水之后的中期提示词。故意写得很懒,看模型自己往哪走。

enhance the overall quality
P3电影感 finalcinematic

出 final HTML 前最后一条。每个走到 final 的模型都跑过。

Improve the ocean/water scene so it feels significantly more realistic, cinematic, and visually rich.

The final result should look like a believable body of water rather than a flat or decorative shader. Focus on making the water feel deep, dynamic, natural, and physically convincing from multiple viewing angles. The surface should have layered motion, subtle variation, convincing highlights, realistic color depth, and a strong sense of scale. Avoid repetitive patterns, plastic-looking shine, overly uniform color, and artificial movement.

Make the lighting, reflections, wave behavior, foam, horizon, and overall composition work together as a polished real-time ocean rendering demo. The goal is not just to add more effects, but to make the water feel alive, immersive, and high quality.

Return the improved result as a complete, self-contained single HTML file that can run directly in the browser.
P4具体 runtime 报错修复runtime fix

只有归档 HTML 在浏览器里报错时才会触发。本次只在 DeepSeek 那条用过一次(`debugSelect is not defined`)。

deepseek_html_20260501_d05add.html:1347 Uncaught ReferenceError: debugSelect is not defined at deepseek_html_20260501_d05add.html:1347:9

The error occurs because `debugSelect` is used in `cycleDebugView()` but was never declared. Fix the standalone HTML so the debug selector is defined and the demo runs directly in the browser.
P5Codex CLI 排队条件codex queue

只有 Codex CLI 这条用。CLI 接受的是排队链,不是回合制。

Codex CLI GPT-5.5 xhigh was tested as one queued-message run in ~/Desktop/codexwater:

1. P0 original benchmark prompt
2. P2 enhance the overall quality
3. P3 final cinematic water prompt

The archived result is the final HTML emitted after that queued chain, not three separately inspected intermediate HTML files.
// run log每条路线的 prompt 链。
  • Claude Opus 4.7 AdaptiveClaude web
    P0P2P3

    P0 首版直接成型;后面三次迭代拿来抛光细节,收在 microfacet final。

  • GPT-5.5 Pro Extended ThinkingChatGPT web
    P0P1P2P3

    P0 翻车 runtime → P1 把水拉回来 → P2 加控件 → P3 收在自包含 WebGL2 final。

  • Codex CLI GPT-5.5 xhighCodex CLI
    P0P2P3

    一次性排队送 P0 → P2 → P3,没有回合制对话,也没有中间版本。

  • GPT-5.5 Thinking StandardChatGPT web
    P0P1P2P3

    P0 翻车在对话里没归档;归档从 P1 修复版开始,P2/P3 抛光。一份拼写笔误的副本卡在模块导入。

  • Claude DesignClaude Design bonus
    P0P3

    当视觉参考看就行,Claude Design 本来就偏艺术方向,不是为工程横评设计的。

  • Gemini 3.1 ProGemini web
    P0P2P3

    三版连出,没翻车。视觉跳得最猛是 P3 那版,指令遵守度相对松一些。

  • DeepSeek web ExpertDeepSeek web
    P0P2P4P3

    P0 → P2 抛光 → P4 修一处 `debugSelect` 没声明的 runtime → P3 final。

  • Kimi 2.6 ThinkingKimi web
    P0P3

    P0 → P3,没翻车。难的 shader 项是直接绕过去了,不是试了出错。

  • Qwen 3.6 Max PreviewQwen web
    P0P1P3

    P0 shader 编译挂掉 → P1 把渲染拉回来 → P3 final 简化版。

  • GLM-5.1Z.ai web
    P0P1

    P0 完全没出 canvas → P1 把渲染拉回来;这轮里没走到干净的 final。

// codex_cli_queueCodex CLI 是排队链,不是聊天。

P0 → P2 → P3 产出一个 final HTML。

Codex CLI queued follow-up inputs
04 · 简短记录

一些轻量观察

短结论,不当排行榜看。

// 个人偏爱Claude Opus 4.7 Adaptive 是我的个人偏爱。

水感、物理和场景可用性比较均衡。

// 最听指令GPT-5.5 Pro Extended Thinking 比较贴 brief。

修复路径和 UI 最稳,但视觉上限没那么高。

// 吸睛单帧Gemini 3.1 Pro 单帧最电影感,但指令一般。

单帧很强,指令完成度一般。

// 视觉参考Claude Design 氛围强,工程不到位。

只当视觉参考:氛围强,工程项不完整。

// 控件Codex CLI 和 DeepSeek 控件更重。

控件很多,但水感还要分路线看。

// 真翻车GLM、Qwen、GPT 首版踩到了真问题。

无 canvas、shader 编译失败、runtime 报错。

// 不必当排行榜看这是一轮快照,不是排行榜。

一台机器,一轮,一套 prompt。

06 · 免责

这是一轮快照,不是排行榜。

一轮快照,只按快照看。

// surfaces

多数路线来自网页端;Codex CLI 单独标注。

// reproducibility

措辞、会话和时间都会影响排序。

// not a leaderboard

这是定性读图,不是正式 benchmark。