superintelligencerobot

AI vs humans scoreboard

Milestone by milestone: where machines have pulled ahead, where they have caught up, and where people still win.

Last updated October 2026

AI is ahead7
AI is level6
Humans are ahead5

AI is ahead

AI beats the best humans in the world.

1997ChessIBM's Deep Blue beat world champion Garry Kasparov. Today's engines are far beyond any human.
2011Jeopardy!IBM's Watson beat the show's two greatest champions.
2016GoDeepMind's AlphaGo beat Lee Sedol, a feat experts expected to be a decade away.
2019PokerPluribus beat elite professionals at six-player no-limit Texas hold'em, a game of hidden information and bluffing.
2019Dota 2OpenAI Five beat OG, the reigning world champion team, in a complex real-time team strategy game.
2020Protein structureDeepMind's AlphaFold predicted 3D protein shapes with near-lab accuracy, earning a share of the 2024 Nobel Prize in Chemistry.
2025Competitive programmingAt the ICPC World Finals, an OpenAI system solved all 12 problems, a result no human team matched.

AI is level

AI performs at expert or skilled-human level, but not clearly above the best.

2015Image recognitionMicrosoft's system beat the estimated human error rate on the ImageNet photo-labeling benchmark.
2017Conversational speech recognitionMicrosoft reported transcription accuracy matching professional human transcribers on a standard benchmark.
2019StarCraft IIDeepMind's AlphaStar reached Grandmaster, ranking above 99.8% of active players.
2023Bar examGPT-4 earned a passing score on the US Uniform Bar Exam.
2025Math OlympiadSystems from Google DeepMind and OpenAI scored at gold-medal level at the International Mathematical Olympiad.
2026Abstract reasoning puzzles (ARC-AGI-2)Top AI systems now beat the average human tester on puzzles designed to resist memorization.

Humans are ahead

Areas where people still clearly outperform AI.

2026Brand-new reasoning games (ARC-AGI-3)Launched in March 2026; humans solve it readily while the best AI systems fall far short.
2026Expert-level exam questionsOn Humanity's Last Exam, built from questions that stump specialists, top AI gets roughly half to about 60% right.
2026Long, open-ended workAI agents handle tasks lasting hours, but still struggle with projects that take a person weeks.
2026Driving anywhereRobotaxis run without drivers in selected cities, but not on every road and in every condition a human can handle.
2026Everyday physical choresFolding laundry or tidying a strange kitchen remains hard for robots. See sirobot.us for where they stand.

The year is when the milestone was reached or, for "Humans are ahead", when the status was last checked. Benchmark scores are reported inconsistently, so we use these three categories rather than precise percentages.