Comment by occamschainsaw

Even o3 can't figure out the naming scheme. When asked to generate names that would be easier to use by non-technical people, it assumed o3 and o4 are the smallest models:

``` Below is one straightforward, user-friendly approach you could adopt. It keeps two dimensions only—generation and tier—and reserves an optional “optimisation” suffix for special-purpose variants (e.g. vision, coding, long-context).

⸻

1. Core conventions

Element Purpose Example values Generation Major architectural release. Keep a whole number; use “.1”, “.2”… for mid-cycle improvements. 4, 4.1, 4.5 Tier Rough capability / cost band, easy to interpret. Lite, Standard, Pro, Ultra Suffix (optional) Special optimisation or domain specialisation. -LongCtx, -Vision, -Code

Why this works • No ambiguous letters or numerics – “o3” can be read as “03” or “oz”; avoid that entirely. • Self-explanatory language – non-technical users recognise “Lite” versus “Pro” instantly. • Scalable – new minor rev? bump the generation (4.2). Need a cheaper size? add a Nano tier without disturbing the rest.

⸻

2. Applying it to your current list

Current name Proposed new name Rationale GPT-4o GPT-4 Standard Baseline flagship of the 4-series. o3 GPT-4 Lite Same generation, lowest tier. o4-mini GPT-4 Lite+ (or GPT-4 Lite LongCtx if that’s the point) Indicates “Lite” family but a bit more capable; “+” or a suffix clarifies how. o4-mini-high GPT-4 Standard LongCtx (or GPT-4 Lite Pro) Pick one dimension: either it’s still “Lite” but higher context, or it has moved into “Standard”. GPT-4.5 GPT-4.5 Standard Mid-cycle architectural upgrade, default tier. GPT-4.1 GPT-4.1 Standard Ditto. GPT-4.1-mini GPT-4.1 Lite Same generation, smaller/cheaper option.

⸻

3. Quick style guide for future models 1. Stick to two words (or two words + optional suffix) GPT-5 Pro, GPT-5 Lite-Vision – still readable at a glance. 2. Reserve extra punctuation for special cases only Hyphens or the “+” symbol should signal meaning, not be decorative. 3. Publish a public matrix A small table in docs or the dashboard that maps Generation × Tier → context length, cost, latency eliminates guesswork.

⸻

One-line summary

GPT- [-Specialisation] keeps names short, descriptive and future-proof—so even non-technical users can tell instantly which model suits their needs. ```