Proof Center

Every pick we've made. Wins and losses.

This page is built live from the same database our picks are saved to — nothing here is typed in by hand. One engine, two jobs: Fight IQ calls a winner in every fight from fighter data alone, and Value flags the fights where the odds disagree with the model. Being right isn't enough, so we also show whether our percentages hold up — when we say 70%, does it hit about 7 times in 10? — and every miss.

Loading latest data…
Two records, clearly labeled. Live picks are written to the database before fight night with their percentage and price — added once, never revised. Everything else is the replay: we re-ran the engine through history year by year, only ever letting it pick fights it had never seen, and graded it at the closing price. The replay's first year is excluded from everything published — the engine wasn't calibrated yet that early, and an uncalibrated number isn't one we'd have shown you. We never show a simulation as if it were live.

Locked before the bell — our real pre-fight record

Not a simulation. Every pick below was saved with a timestamp before the card started, then graded against what actually happened — misses and all. Pick a model to see its genuine pre-fight record.
Loading the locked pick record…
Crunching the graded record…
Every model we've run — archived simulations
Every model we've ever run, oldest to newest. These records are simulations — each model re-run over history, not picks locked before fights — so we grade each only on fights after it was finished, the ones it never trained on. Where a model's exact cutoff isn't confirmed, we start it at Jan 2025 to be safe, so no model can score itself on data it already saw. The one genuinely locked-before-the-bell record is the pre-fight section at the top of this page.

Read the high numbers with suspicion, not pride. The models that score highest here (v5 and v6) do so because our own audit found they leaned on the closing betting line or graded themselves partly on fights they trained on — the exact cheating we walked away from. The engine's lower, honest number is the one we stand behind.
Crunching the full pick history…

Did we beat the closing price?

The toughest test of a betting model: we take -150, it closes at -180, we got the better price. Do our picks do that over and over?
Every live Value pick locks its price the moment we post it, and we compare it to the closing price after the card. That sample is still too small to mean anything, so we're not going to dress it up as proof — these numbers go up here once 100+ locked picks have both a posted price and a closing price on record. Until then, judge us on the graded record above.

How to read this honestly

The record is the pitch.Put the model to work on the next card — every pick, edge, and price in one place.

Model probabilities are statistical estimates, not guarantees. Historical performance does not predict future results. Cannon Fight Lab is an analytics publication, not a sportsbook, and nothing on this page is betting advice. 21+ only.