Pietro Bardone

p3pp01

https://serpie.it

https://github.com/p3pp01

AI & ML interests

I'm a human intelligence, but not so intelligent

Recent Activity

updated a Space 14 days ago

p3pp01/First_agent_template

published a Space 19 days ago

p3pp01/First_agent_template

reacted to eugenesiow's post with 👀 4 months ago

GPT-4.1 dropped this week - and it puts OpenAI back in the race for coding & agentic leadership. ⚙️ API only - no ChatGPT toggle for this. 💻 Coding performance is back on par with Claude 3.7 Sonnet & Gemini 2.5 Pro (though Gemini still leads). 💸 Pricing: • Full: $3.50 / 1M tokens • Mini: $0.70 / 1M • Nano: $0.17 / 1M 👉 Gemini 2.5 Pro = best price/perf ($3.44 / 1M) 😵 Claude 3.5 Sonnet = $6 / 1M (!) 🧠 Not a "thinking" model. 📊 Mini shines on general reasoning tasks (e.g. GPQA), but only the full model holds up in SWE-bench-verified (GitHub issue solving).

View all activity

Organizations

None yet

updated a Space 14 days ago

First Agent Template

⚡

Fetch current time in any timezone

published a Space 19 days ago

First Agent Template

⚡

Fetch current time in any timezone

reacted to eugenesiow's post with 👀 4 months ago

Post

1686

GPT-4.1 dropped this week - and it puts OpenAI back in the race for coding & agentic leadership.

⚙️ API only - no ChatGPT toggle for this.
💻 Coding performance is back on par with Claude 3.7 Sonnet & Gemini 2.5 Pro (though Gemini still leads).
💸 Pricing:
• Full: $3.50 / 1M tokens
• Mini: $0.70 / 1M
• Nano: $0.17 / 1M
👉 Gemini 2.5 Pro = best price/perf ($3.44 / 1M)
😵 Claude 3.5 Sonnet = $6 / 1M (!)

🧠 Not a "thinking" model.
📊 Mini shines on general reasoning tasks (e.g. GPQA), but only the full model holds up in SWE-bench-verified (GitHub issue solving).