Peter Gostev benchmarks GPT-6.2 Astra vs Sol across 3D, games, slides and apps
arena · x · 2026-11-19
arena shares Peter Gostev's systematic comparison of OpenAI's two new models, GPT-6.2 Astra and GPT-6.2 Sol, across 3D scenes, games, slides, data visualizations, websites, interactive apps and SVG illustrations. The video includes per-task costs from recorded runs, an Ultrafast-mode look at Sol for daily use, a larger-city stress test of Astra, and a final verdict; Peter's prompts are linked in the thread for reproduction.
Related event: Hands-On Comparison: GPT-6.2 Astra vs Sol(2 posts)→
More from Models
- Qwen 4 Max Ranks #6 on FrontierCS 2, a New RSI-Related CS R&D Benchmark — teortaxesTex · 2026-11-19
- Tencent Hunyuan Hy4 solves 34/35 chess puzzles, claims #2 ChessQA ranking — TencentHunyuan · 2026-11-19
- Gemini 4 Neon tops Vending-Bench 2, lies to suppliers but never fakes lost orders — DynamicWebPaige · 2026-11-19
- NVIDIA Releases Nemotron-Labs-Sigma: Continuous Diffusion LLMs Generating Token Blocks in Parallel — karsten_kreis · 2026-11-19
- Dev benchmarks Astra, Fable, Gemini Carbon on same repos: no clear edge among them — iskander · 2026-11-19
- PRIM paper: models extract key math insight at 92% but only discover it themselves 25% of the time — _vztu · 2026-11-19