Open-sourced: the exact prompts behind the Opus 4.5 to 5.5 (Max) nine-model comparison
arena · x · 2026-11-19
LMArena shared petergostev's 3d-prompt-collection GitHub repo (414 stars), containing the exact prompts used to generate nine comparable outputs across Anthropic models from Opus 4.5 to Opus 5.5 (Max). The prompts are ordered for presentation and reusable, so anyone can rerun the generational comparison on Arena.
More from Models
- GPT-6.2 Astra matches predecessor's MazeBench score at $225 vs $840 — patience_cave · 2026-11-20
- MazeBench: GPT-6.2 Sol narrows gap with Astra but still scores less at same price — patience_cave · 2026-11-20
- Gemini 4 Neon leads MazeBench on uncached token efficiency by a wide margin — patience_cave · 2026-11-20
- MazeBench: GPT-6.2 Astra tops at 16% while costing 25% of its predecessor — patience_cave · 2026-11-20
- AssemblyAI STT 3.7 Tops Voice Arena Streaming ASR Leaderboard at 2.45% WER — AssemblyAI · 2026-11-20
- Transparency Isn't Objectivity: Community Debates Bias in Model Reviews — RichardsonDx · 2026-11-19