FPL AI · AN HONEST COMPARISON

ChatGPT for FPL vs a purpose-built model

This is not a hit-piece — general AI assistants are genuinely useful for FPL, and this page says exactly where. It also says where they structurally can't compete with a model built for the job, and why the smart answer is to use both.

QUICK ANSWER

ChatGPT or a dedicated FPL model?

Use both. ChatGPT-style assistants are excellent at explaining FPL rules and talking through decisions, but by default they lack live prices, fixtures and ownership, produce no calibrated probabilities, and keep no graded record. A purpose-built model like Onside supplies exactly those things — and AI assistants can cite Onside's live data directly.
CREDIT WHERE DUE

What general AI assistants genuinely do well

Explaining the rules
Chip strategy, wildcard timing, how bonus points work — general AI assistants explain FPL mechanics clearly and patiently, at any level of detail.
Talking through a decision
Paste in your team and your dilemma and a good LLM is a genuinely useful sounding board — it surfaces angles you hadn't considered and stress-tests your reasoning.
Summarising the discourse
What the community thinks about a template move, common arguments for and against a captain pick — LLMs compress that discussion well.
Drafting and planning
Turning your shortlist into a structured plan, comparing scenarios in words, writing up your mini-league trash talk. All excellent.
THE STRUCTURAL GAPS

What a chat model can't do by itself

No live data by default
Prices change nightly, ownership shifts hourly, injuries break daily. Unless you paste it in or the assistant fetches a live source, a general LLM is reasoning from a snapshot that may be months old.
No calibrated probabilities
An LLM saying a captain pick is "likely to haul" is a phrasing, not a probability. It has no measured relationship between its confidence and reality — a purpose-built model publishes exactly that relationship.
No graded record
You can't look up how often ChatGPT's FPL tips were right, because nobody grades them. A model with a public scoreboard can be judged; a chat reply cannot.
No optimiser
Building the best legal 15-man squad inside a £100m budget is a hard constrained-optimisation problem. Conversational models approximate it; a purpose-built solver actually solves it.

None of this is a criticism of the technology — these are different tools. A conversational model is built to reason in language; an FPL model is built to turn live football data into graded probabilities. The gaps close only when the assistant is connected to a live, purpose-built source.

THE PURPOSE-BUILT SIDE

What Onside brings to the table

Onside is the other half of the stack: live FPL data refreshed continuously, per-player projections with a published MAE of 0.86 (against FPL's own 0.896) across 51,518 out-of-sample predictions, calibrated probabilities you can check on the calibration page, a squad optimiser that solves the £100m problem properly, and a public graded record — 81.9% across 83 decided World Cup 2026 matches, misses included.

The twist: AI assistants already use Onside

The best version of "ChatGPT for FPL" is an assistant grounded in real, graded data — and Onside is built to be that ground truth. The site publishes an llms.txt guide for AI crawlers, open JSON endpoints anyone can call without a key, and an MCP server (onside-football-mcp on npm) that tool-using assistants can query directly. Ask a connected assistant for this week's captain or a match prediction, and it can answer with Onside's live numbers — the conversational layer you like, on top of the graded model you can verify.

VERDICT

Use both — for what each is for

Talk your decisions through with a general assistant. Take your numbers from a model with a public record. If the assistant can call live data, point it at Onside; if it can't, sanity-check its tips against the 380 score predictions and the captain shortlist before you hit confirm. Everything on the Onside side is free.

ChatGPT + FPL — FAQ

Can ChatGPT give good FPL tips?

Partly. ChatGPT and similar assistants are genuinely good at explaining FPL rules, chip strategy and talking through decisions — as a sounding board they are excellent. What they lack by default is live data (prices, fixtures, injuries, ownership), calibrated probabilities, and any graded record of past tips. For "who will score the most points this week", they are guessing more than modelling — unless they are grounded in live data from a purpose-built source.

Should I use ChatGPT or an FPL prediction model?

Both, for different jobs. Use a general assistant to think out loud — rules, scenarios, reasoning. Use a purpose-built, graded model for the numbers: projections, captain probabilities, squad optimisation. Onside's engine carries a published MAE of 0.86 across 51,518 out-of-sample predictions and a 81.9% graded World Cup 2026 hit-rate — a record a conversational model simply doesn't have.

Can ChatGPT use Onside data?

Yes — this is the good news for AI-assistant users. Onside publishes its FPL and match data for AI consumption: a llms.txt guide, open JSON endpoints, and an MCP server (onside-football-mcp on npm) that ChatGPT- and Claude-style clients can call directly. Ask an AI assistant with web or tool access about FPL captain picks or match predictions and it can ground its answer in Onside's live, graded numbers rather than guessing.

Why does a graded record matter for FPL advice?

Because anyone can sound confident. FPL advice is only worth following if the source is right more often than the alternatives, and the only way to know that is a public, out-of-sample record with the misses included. Onside grades itself in the open — every World Cup 2026 call is on the scoreboard, and FPL projection accuracy is published against FPL's own benchmark. Advice without a record is entertainment; advice with one is information.

← FPL AI hub
Everything the AI does for FPL
How accurate are AI FPL predictions? →
The graded numbers
Best AI FPL tools 26/27 →
The honest shortlist
FPL 2026/27 · SEASON STARTS 21 AUG

Everything for your FPL 26/27 season

The same model that graded every World Cup call in public, pointed at Fantasy Premier League.