OpenAI · 9 models tested
Which OpenAI model should you use?
OpenAI's strongest model is GPT-5.5 (avg percentile 88, top-3 in 7 of 22 task areas). On a budget, GPT-5.4 stays close at $17.5/1M.
The OpenAI lineup, ranked
| Model | Overall | Code & data | Writing & comms | Business & strategy | Creative & visual | AA Intel† | Top-3s | Price / 1M |
|---|---|---|---|---|---|---|---|---|
|
GPT-5.5
Best overall
22 task areas
|
88 | 86★ | 92★ | 82 | 96★ | 55 | 7 | $35.0 |
|
GPT-5.4
Best value
22 task areas
|
83 | 82 | 87 | 82★ | 80 | 51 | 3 | $17.5 |
|
GPT-5.4 Mini
22 task areas
|
64 | 73 | 75 | 61 | 47 | 40 | 2 | $5.25 |
|
GPT-5.5 Pro
6 task areas
|
62 | — | 94 | 46 | 69 | — | 1 | $210.0 |
|
GPT-5 Mini
22 task areas
|
51 | 68 | 36 | 53 | 53 | — | 1 | $2.25 |
|
GPT-5.4 Nano
6 task areas
|
23 | — | 37 | 20 | 20 | 38 | 0 | $1.45 |
|
o1
1 task areas
|
7 | — | — | — | 7 | — | 0 | $75.0 |
|
GPT-4o
1 task areas
|
2 | — | — | — | 2 | — | 0 | $12.5 |
|
GPT-4o Mini
1 task areas
|
0 | — | — | — | 0 | — | 0 | $0.75 |
Area figures are mean percentile ranks; 85+ 70–84 55–69 40–54 <40 · ★ = the lineup's best in that area. †AA Intel = Artificial Analysis Intelligence Index, third-party reference only.
Best OpenAI model, task by task
The lineup's strongest model in each task area — and where it lands against every model we test, not just OpenAI's. #1 means it beats every rival lab too.
Where another lab clearly wins
Honesty corner: the task areas where even OpenAI's best model ranks furthest from the top. See who actually leads there.
Frequently asked
What is the best OpenAI model?
GPT-5.5 — the highest average percentile (88) across the task areas we benchmarked, with 7 top-3 finishes.
What is the best cheap OpenAI model?
GPT-5.4: within 5 percentile points of GPT-5.5 at $17.5 per 1M tokens.
Where does OpenAI lead every other lab?
A OpenAI model holds the outright #1 spot in 7 task areas: Chef / Home Cooking, Coding, Knowledge & Docs, Presentations & Decks, Product & Project Management, Research & Competitive Analysis, Structured Output.
This page is Spring Prompt, running
We just did this for every model. Do it for your prompt.
The rankings above come from running real tasks through real models and scoring every output. Spring Prompt is that same engine — pointed at your prompt, your test cases, and your definition of good.
- Generate test cases from your prompt — no eval set required to start.
- Compare models side by side with quality, cost and latency in one matrix.
- Optimise the winner until the scores say it's ready to ship.
Prompt × model results
12 test cases · 3 evals