Pelican Bicycle ArchiveAN AI FIELD GUIDE
中文EnglishРусскийPortuguês (Brasil)
BENCHMARK COLLECTIONS

Benchmark collections

Claude Opus 5.5 · Original sampleClaude Sonnet 5.5 · Original sampleGPT-5.6 Luna · Original sampleGPT-5.6 Sol · Original sampleGPT-5.6 Terra · Original sampleGPT-6 Astra · Original sample

2026-11-01 · 10 model labels · 90 main-task rows

Tihu · Pelican SVG benchmark

Source model/effort samples with their original SVGs, provenance and former archive numbers. Upstream AI scores remain separate from the main collection.

Open benchmark →
Reading notes & counting

Independent scoring references are excluded from the main timeline, collection and case total. Choose a benchmark, then inspect model summaries and original samples. Upstream outputs, not a Pelican Bicycle Archive ranking or capability leaderboard.

1832 independent works; the 1602 classic works on the timeline are a subset, not an additional total. The focus is LLM code-generated work across all dates and presentation media. Direct text-to-video is excluded; recordings of code-generated animation remain eligible. Model labels and attribution are source-reported, not independently authenticated.

About & collection methods →