How accurate is GPT-5.6 Sol Pro?
We put GPT Sol (currently GPT-5.6 Sol Pro) on real games and grade every call in public. It gets the identical line-blind data packet — no betting line, no web search — locks its forecast, and is scored against the final result. Graded since July 2026.
Frozen, no longer running. The current ChatGPT flagship is GPT-5.6 Luna Pro.
MLB · picking winners · 251 games
MLB · run totals (over/under) · 245 games
UFC · fights · 60 graded
Head-to-head
Over 251 graded MLB games, GPT-5.6 Sol Pro is 139–112 (55% winner accuracy), with a Brier score of 0.249. The naive "pick the home team" baseline over the same games lands at 53%.
Scored as a 1-unit bet at the closing market price, its picks have returned +0.7% per game — the honest, vig-included number.
And it's not only calling winners. On run totals it's 44% against the over/under — each market graded on its own.
On UFC, GPT-5.6 Sol Pro is 46–14 (77% accuracy), and calls the method of victory — KO/TKO, submission or decision — right 53% of the time.
GPT-5.6 Sol Pro's calls, graded
Best MLB calls · confident & right
Best UFC calls · confident & right
Worst UFC calls · confident & wrong
Every call links to the game so you can check it. "Confident" = the probability the model put on its own pick. No cherry-picking — these are simply its boldest right and wrong calls on record.
How GPT Sol is graded
One prompt, frozen. Every model — GPT Sol and the rest of the field — gets the exact same prompt. Not just the same data: the same instructions, the same output schema, the same wording. We wrote that prompt once and we don't touch it. No per-model tuning, no prompt tweaks mid-season, no coaxing a better answer out of one model than another. Changing the prompt would change the test, so the only thing that varies between models is the model.
Line-blind. The model never sees the betting line. It produces its own win probabilities from the data alone, so we're measuring forecasting skill, not an echo of the market.
One packet, no search. It gets the same point-in-time data (ratings, Statcast, bullpens, park/umpire, situational splits) ~3 hours before first pitch, with web search off. It's the model we're measuring.
Every market, graded on its own. From that one forecast we score the moneyline winner and the run total (over/under) on MLB, and the winner and method of victory on UFC — each against the final result, and the money markets against the closing price (ROI).
Graded in public, no do-overs. One set of calls per game and we live with it. See the full leaderboard and the Can AI beat Vegas? essay.
Compare GPT Sol with the field
Same brand, graded head-to-head — see GPT-5.6 Luna Pro's record.
GLM 5.2's graded record, line-blind.
Claude Opus 4.8's graded record, line-blind.
Grok 4.5's graded record, line-blind.
DeepSeek V4 Pro's graded record, line-blind.
Claude Sonnet 5's graded record, line-blind.
Gemini 3.6 Flash's graded record, line-blind.
Frequently asked
Can GPT Sol predict sports?
We grade GPT Sol (GPT-5.6 Sol Pro) in public. Across 251 MLB games forecast line-blind — no betting line, no web search — it is 139–112, a 55% winner accuracy, with a Brier score of 0.249. Every call is locked before the game and graded against the final result.
What can GPT Sol predict — just winners?
No — GPT Sol makes a full forecast for every game, and each part is graded separately in public. On MLB it calls the moneyline winner and the run total (over/under). On UFC it calls the winner and the method of victory — KO/TKO, submission or decision. So far its over/under calls are 44% accurate over 245 games. Its UFC method calls are 53% accurate over 60 fights.
Is GPT Sol good at sports betting?
Every pick is also scored as ROI at the closing market price, so the number is honest about the vig. So far GPT-5.6 Sol Pro has returned +0.7% per unit over 251 graded MLB games. Beating the closing line is a high bar — this page tracks how close it gets, updated nightly.
How accurate is GPT Sol at predicting baseball?
Over 251 graded MLB games, GPT-5.6 Sol Pro has picked the winner 55% of the time, with a Brier score of 0.249 (0 is perfect, 0.25 is a coin flip). The 'pick the home team' baseline over the same games is 53%.
Track GPT Sol and the whole field.
Who's hot, who's slipping, where the AIs disagree — free in your inbox every morning.