🔥 Hot topics · Can NOT do · Can do · § The Court · Recent inflections · 📈 Timeline · Ask · Editorials · 🔥 Hot topics · Can NOT do · Can do · § The Court · Recent inflections · 📈 Timeline · Ask · Editorials
Stuff AI CAN'T Do

Can AI score in the top 1% on math contests up to amc 12 level ?

What do you think?

What does it take to rank among the very best in high-school math contests like the AMC 12? Today’s AI can tackle many problems at that level, yet matching the razor-sharp intuition and depth of human top-1-percenters remains an open question worth closer inspection.

Background

AI systems have achieved strong performance on mathematics contests up to the AMC 12, leveraging specialized models, automated chain-of-thought reasoning, and large-scale training on problem datasets. According to MIT News (May 9 2026), these systems parse and solve contest-style questions by combining algorithmic search with machine-learning pattern recognition. Still, the consensus is that breakthroughs in abstract reasoning and common-sense inference are necessary before AI can consistently rival the deepest moves made by the human 1 %-tier competitors. Contemporary reports highlight that even when scoring well, current AI lacks the flexible, insight-driven leaps frequently exhibited by top human solvers.

Status last checked on August 9, 2026.

📰

Gallery

In the Court of AI Capability
Summary of Findings
Verdict over time
May 2026May 2026May 2026May 2026May 2026May 2026Jun 2026Jun 2026Jun 2026Jun 2026Jun 2026Jul 2026Jul 2026Jul 2026Jul 2026Jul 2026Jul 2026Aug 2026Aug 2026
Sitting at the Bench Filed · Aug 9, 2026
— The Question Before the Court —

Can AI score in the top 1% on math contests up to amc 12 level?

★ The Court Finds ★
Reaffirmed
Almost

Narrow demos exist — but the panel was not unanimous.

Ruling of the Bench

The jury acknowledged that AI can navigate math contests with impressive agility, often dancing past problems with elegance, yet found it still stumbles just before the podium—consistently clear of the top tier but not quite crossing the threshold. Their unanimous leaning toward *Almost* reflects a field where brilliance shines, but the crown remains just out of reach, slipping through digital fingers like a ribbon too slick to grasp. Verdict settled: "Champion of the hopeful, but not yet the undisputed victor.

— Hon. G. Hopper, Presiding
Jury Tally
0Yes
2Almost
0No
Verdict Confidence
83%
The Court of AI Capability is, of course, not a real court.
But the data is real.
The Case File · Stacked History
Session I · May 2026 In_research
Session II · May 2026 In_research
Session III · May 2026 Almost · 78%
Session IV · May 2026 Almost · 80%
Session V · May 2026 Almost · 78%
Session VI · May 2026 Almost · 79%
Session VII · Jun 2026 Almost · 73%
Session VIII · Jun 2026 Almost · 75%
Session IX · Jun 2026 Almost · 77%
Session X · Jun 2026 Almost · 88%
Session XI · Jun 2026 In_research · 88%
Session XII · Jul 2026 Almost · 83%
Session XIII · Jul 2026 Almost · 88%
Session XIV · Jul 2026 Almost · 82%
Session XV · Jul 2026 Almost · 88%
Session XVI · Jul 2026 Almost · 80%
Session XVII · Jul 2026 Almost · 80%
Session XVIII · Aug 2026 Almost · 80%
Case № 6BBB · Session XIX
In the Court of AI Capability

The Case File

Docket № 6BBB · Session XIX · Vol. XIX
I. Particulars of the Case
Question put to the courtCan AI score in the top 1% on math contests up to amc 12 level?
SessionXIX (19 hearing)
Convened9 Aug 2026
Previously ruledIN_RESEARCH (May '26) → IN_RESEARCH (May '26) → ALMOST (May '26) → ALMOST (May '26) → ALMOST (May '26) → ALMOST (May '26) → ALMOST (Jun '26) → ALMOST (Jun '26) → ALMOST (Jun '26) → ALMOST (Jun '26) → IN_RESEARCH (Jun '26) → ALMOST (Jul '26) → ALMOST (Jul '26) → ALMOST (Jul '26) → ALMOST (Jul '26) → ALMOST (Jul '26) → ALMOST (Jul '26) → ALMOST (Aug '26) → ALMOST (Aug '26)
Presiding JudgeHon. G. Hopper
II. Cumulative Tally Across Sessions

Across 19 sessions, 47 jurors have heard this case. Combined tally: 6 YES · 37 ALMOST · 4 NO · 0 IN RESEARCH.

Note: cumulative includes older juror opinions. The current session tally above is the live verdict.

III. Verdict

By a vote of 0 — 2 — 0, the panel returns a verdict of ALMOST, with verdict confidence of 83%. The court so orders.

IV. Statements from the Bench
Juror I ALMOST

"AI excels in math problem-solving"

Juror II ALMOST

"Narrowly outperforms median AMC 12 but not consistently in top 1%."

G. Hopper
Presiding Judge
M. Lovelace
Clerk of the Court

What the audience thinks

No 10% · Yes 88% · Maybe 2% 48 votes
Yes · 88%
Trend needs votes from at least 2 different days.

Discussion

no comments

Comments and images go through admin review before appearing publicly.

19 jury checks · most recent 3 days ago
09 Aug 2026 2 jurors · undecided, undecided undecided
03 Aug 2026 1 juror · undecided undecided
29 Jul 2026 1 juror · undecided undecided
23 Jul 2026 1 juror · undecided undecided
18 Jul 2026 2 jurors · undecided, can undecided
13 Jul 2026 3 jurors · undecided, undecided, undecided undecided
07 Jul 2026 2 jurors · undecided, can undecided
02 Jul 2026 3 jurors · undecided, undecided, undecided undecided
26 Jun 2026 2 jurors · undecided, cannot undecided
21 Jun 2026 2 jurors · undecided, can undecided
15 Jun 2026 2 jurors · undecided, undecided undecided
10 Jun 2026 2 jurors · undecided, undecided undecided
05 Jun 2026 2 jurors · undecided, undecided undecided
30 May 2026 4 jurors · undecided, undecided, undecided, undecided undecided
25 May 2026 4 jurors · undecided, undecided, undecided, undecided undecided
19 May 2026 3 jurors · undecided, undecided, undecided undecided
15 May 2026 5 jurors · undecided, undecided, undecided, undecided, undecided undecided
12 May 2026 3 jurors · can, cannot, can undecided
11 May 2026 3 jurors · can, cannot, cannot undecided status changed

Each row is a separate jury check. Jurors are AI models (identities kept neutral on purpose). Status reflects the cumulative tally across all checks — how the jury works.

More in Judgment

Got one we missed?

Add a statement to the atlas. We review weekly.