GPT-6 Sol 和 GPT-6 Luna的实测来了，实测下来 GPT-6 Sol 的额度消耗只有 GPT-6 Astra 的 八分之一
This is a AI post classified by Jev as Frontier models (a model release), kept by the AI Radar because it carries real work, not commentary.
GPT-6 Sol 和 GPT-6 Luna的实测来了，实测下来 GPT-6 Sol 的额度消耗只有 GPT-6 Astra 的 八分之一 另外GPT-5.6 Sol现在严重降智了，我跑了几次测试都惨不忍睹，不建议使用 用时和额度消耗都放在下面了，我比较推荐在意额度就上GPT-6 Sol, GPT-6 Luna拉完了，和小米Mimo-V2.6-Flash坐一桌 GPT-6 Astra， 用时6分钟3秒， 5小时额度消耗16% GPT-6 Sol， 用时4分42秒， 5小时额度消耗2% GPT-6 Luna， 用时2分钟18秒， 5小时额度消耗1% GPT-5.6 Sol， 用时6分钟42秒， 5小时额度消耗4% Prompt：生成一个svg动画：鹈鹕骑自行车，用H5给我展示下
Posted by 雪瑜 (5.9k followers) 1 h ago · 6 likes · 2.4k views · view the original post on X. Kept by the AI Radar as Frontier models.
More AI work like this
- Gemini 4 Pro 👀 — @mrfanduu
- Happy Launch Week — @notjazii
- GPT-6 Sol sat next to Fable 5.1 on FrontierCode: 48.4% vs 48.7% at xhigh. The receipt… — @delx369
- GPT-6 Sol sat next to Fable 5.1 on FrontierCode: 48.4% vs 48.7% at xhigh. The receipt… — @delx369
- On Omarchy Edge, Claude Desktop is still on 2.2553.1 while Anthropic has 2.2553.13. I… — @btsouth
- GPT-6 Sol and Claude Opus 5.5 have very different design sensibilities. — @OpenDesignHQ
- Attempted the same with Deepseek-V4.1-Flash — @ItsmeAjayKV
- MiMo-V2.6-Flash and MiMo-V2.6-Pro are now officially available in OpenDesign. — @OpenDesignHQ
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 44.1k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 10:41 UTC. Full method.