The Spring Prompt Blog

GPT-5.6 Luna Was Meant to Be Fast. It Still Lost to the Clock.

Luna arrived as the fastest GPT-5.6. Across 96 BulletBench games, it lost 71 on time. The result exposes the model the market still has not built: genuinely smart, sub-second and predictable.

Read More

BulletBench: we made 23 AI models play speed chess, and the clock was the judge

Every leaderboard measures how smart a model is. None measure how smart it is per second. So we built one: AI models play speed chess on a real clock, and slow genius loses on time.

Read More

Sonnet 5 gave the sharpest marketing analysis we've ever tested. It also lost money every single time.

A ROASBench case study in why fluent reasoning isn't the same as good decisions, and why for this model more thinking made it worse.

Read More

How We Built ROASBench to Feel Like Real Growth Work

ROASBench was built from operator experience, not benchmark theater. We designed it to feel like real performance marketing: stateful, constrained, path-dependent, and economically unforgiving.

Read More

Claude vs Gemini vs GPT in a 12-Month Marketing Simulation

ROAS Bench is one of the clearest examples of where frontier models diverge in practice: not on prose quality, but on economic compounding.

Read More

LiteLLM alternatives for 2026

If you’re looking for LiteLLM alternatives, you’re usually trying to solve one of two problems: * you need a Python library that makes it easy to switch between LLM providers * you need an AI gateway / routing layer that handles fallbacks, caching, observability, and control That split matters, because the best LiteLLM alternative depends on which problem you actually have. Recent context: On March 24, 2026, LiteLLM disclosed a supply-chain incident affecting malicious PyPI releases 1.82.7 

Read More

Why Most LLMs Still Can't Run Growth

ROAS Bench shows that growth is not a copywriting problem. It is a compounding systems problem, and most models still break the system faster than they improve it.

Read More

The AI Marketing Benchmark That Punishes Plausible-Sounding Strategy

Most LLMs can sound like a competent growth lead for one turn. ROAS Bench is interesting because it makes them live with the consequences for twelve months.

Read More

Gemini Embedding 2 Just Launched - So We Benchmarked It

Google launched gemini-embedding-2-preview on March 10, 2026 as its first multimodal embedding model, with one shared embedding space for text, images, video, audio, and PDFs. Google specifically positions it for cross-modal semantic search, document retrieval, and recommendation-style similarity tasks. That made it a pretty obvious model to test on two things we care about a lot at Spring Prompt: 1. RAG over mixed-media documents 2. Search flows where users combine text and images So inste

Read More

The Great AI Gifting Showdown: Which Model Should You Trust for Christmas Shopping?

It’s that time of year again. You’re out and about, the clock is ticking, and you still haven't found the perfect gift for your partner, your roommate, or that difficult-to-shop-for in-law. Naturally, many of us are turning to AI chatbots to brainstorm ideas. But not all AIs are created equal when it comes to the nuances of gift-giving. Does ChatGPT understand "thoughtfulness"? Can Claude actually predict what your brother wants, or just what he needs? We ran a rigorous test using Spring Promp

Read More