qingming-bianjing
同一份提示词，两座汴京：Claude Opus 5.5 与 GPT 6 Sol 各自从零写出的《清明上河图》实时 3D 网页 · Same prompt, two cities — a real-time 3D Bianjing benchmark for LLMs
Details
- External ID
- 1382973385
- Source
- GITHUB
- Company
- —
- Product
- qingming-bianjing
- Website domain
- github.io
- Launched
- Sept. 23, 2026
- Cohort
- —
- Upvotes
- 8
- Upvotes percentile
- 0.14514476044068664
- Tags
- benchmark, generative-ai, llm, procedural-generation, threejs, webgl
- Fetched at
- Sept. 27, 2026, 5:03 p.m.
- Updated at
- Sept. 27, 2026, 5:03 p.m.
Enrichment
- Theme
- ML inference and model optimization
- Vertical
- Horizontal
- Function
- Observability & eval
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- 3d scene generation benchmark for llms
- Manually corrected
- False
Could you build this?
Yes The project is a static comparison showcase website featuring 3D WebGL/Three.js scenes generated from prompts by LLMs. Hosting and rendering existing generated 3D scenes or running prompt evaluations is standard web front-end work that can be easily vibe-coded.
Competitors
Other products that read as similar to this one — 410 launches clear the similarity bar, closest 8 shown.
Attention rank: #307 of 411 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 323 days after the earliest competitor.
- qingming · github · 2026-09-12 · 10 upvotes · similarity 0.51
- stratum · github · 2026-09-18 · 11 upvotes · similarity 0.46
- LLMExperiments · github · 2026-09-24 · 7 upvotes · similarity 0.44
- Minimal LLM Post-Training Experiments on an 8GB GPU (SFT, DPO, GRPO) · hn · 2026-08-01 · 21 upvotes · similarity 0.44
- MathmoBench · github · 2026-09-23 · 88 upvotes · similarity 0.44
- three-avbd · github · 2026-09-24 · 48 upvotes · similarity 0.44
- Strata · hn · 2026-07-09 · 8 upvotes · similarity 0.43
- A zero-to-hero, spaced-repetition guide to WebGL2 and GLSL · hn · 2025-12-12 · 5 upvotes · similarity 0.43
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a observability & eval tool for Media & entertainment yet.