AI · resolved market
Will any OpenAI GPT model score at least 50% on the FrontierMath Exam?
https://tailmypicks.com/m/0x59934f09e5664784e6c2ed9e3bbff7e7fd4dac0419969bc5db3802a2eff73160
Rebuilt .
What this market resolved to
- Winning outcome
- Yesof Yes, No
- Resolved
- US/Eastern, the zone Polymarket writes its markets in
- Scored in
- AIevery record on this page is that Category’s
- Volume Polymarket published
- Polymarket published no figure
- Volume TailMyPicks’s own read summed
- $9,915
Both are shown because TailMyPicks only trusts a market it can reconcile: it reads every trade itself and compares its own total against the venue’s before scoring anything. The threshold below was applied to $9,915 — TailMyPicks’s own total, because the venue published none.
Every figure here describes what TailMyPicks scored — positions held to resolution in markets that cleared the thresholds below. It is not a Polymarket account balance, and open positions are not counted anywhere on this site.
Who was on this market
All 26 wallets that hold a qualified pick on this market, biggest position first. Ordered by position size rather than by score, because this is a post-mortem of one market — a strong wallet’s small pick does not belong above a large committed one. Each wallet’s record in AI is on its own row, so one correct call here is not mistaken for a track record.
| On this market | This wallet’s whole record in AI | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Wallet | Entry | Position | Result | P/L held | Qualified picks | Win rate | vs expected | Realizable edge | Avg entry | ROI per pick | Tail Score |
| 0x0a7a…df1bbacked No | 1c | 1,250$18 in | Lost — open this pick on its own page | -$17.5 | 217 | 13.4%29 W · 188 L | +8.1wins | +0.04per pick | 10cpaid | +2.5%equal weight | 54+0.03 edge/pick |
| 0xe154…0b7fbacked No | 3c | 994.51$25 in | Lost — open this pick on its own page | -$24.89 | 263 | 12.9%34 W · 229 L | +5.5wins | +0.02per pick | 11cpaid | -1.4%equal weight | 52+0.02 edge/pick |
| 0xddc2…ac29backed Yes | 37c | 174$64 in | Won — open this pick on its own page | +$109.62 | 1 | 100%1 W · 0 L | +0.6wins | +0.63per pick | 37cpaid | +170.3%equal weight | 53+0.02 edge/pick |
| 0xe2dc…fda4backed Yes | 37c | 172$64 in | Won — open this pick on its own page | +$108.36 | 1 | 100%1 W · 0 L | +0.6wins | +0.63per pick | 37cpaid | +170.3%equal weight | 53+0.02 edge/pick |
| 0x36c7…d48ebacked Yes | 37c | 168$62 in | Won — open this pick on its own page | +$105.84 | 1 | 100%1 W · 0 L | +0.6wins | +0.63per pick | 37cpaid | +170.3%equal weight | 53+0.02 edge/pick |
| 0x4396…622fbacked Yes | 37c | 159$59 in | Won — open this pick on its own page | +$100.17 | 1 | 100%1 W · 0 L | +0.6wins | +0.63per pick | 37cpaid | +170.3%equal weight | 53+0.02 edge/pick |
| 0x93b3…b9d0backed Yes | 37c | 153$57 in | Won — open this pick on its own page | +$96.39 | 1 | 100%1 W · 0 L | +0.6wins | +0.63per pick | 37cpaid | +170.3%equal weight | 53+0.02 edge/pick |
| 0xc42f…78a0backed No | 52c | 117$61 in | Lost — open this pick on its own page | -$61.02 | 76 | 36.8%28 W · 48 L | +4.9wins | +0.06per pick | 30cpaid | +6.9%equal weight | 55+0.05 edge/pick |
| 0x21d5…6f93backed Yes | 51c | 108$55 in | Won — open this pick on its own page | +$53.32 | 60 | 16.7%10 W · 50 L | -4.6wins | -0.08per pick | 24cpaid | -67%equal weight | 44-0.05 edge/pick |
| 0xad53…ef24backed Yes | 45c | 81.94$37 in | Won — open this pick on its own page | +$45.35 | 893 | 17.1%153 W · 740 L | -144.9wins | -0.16per pick | 33cpaid | -61.3%equal weight | 32-0.16 edge/pick |
| 0x265d…7da5backed No | 63c | 70$44 in | Lost — open this pick on its own page | -$44.1 | 1 | 0%0 W · 1 L | -0.6wins | -0.63per pick | 63cpaid | -100%equal weight | 47-0.02 edge/pick |
| 0x1a56…82dabacked No | 63c | 69$43 in | Lost — open this pick on its own page | -$43.47 | 1 | 0%0 W · 1 L | -0.6wins | -0.63per pick | 63cpaid | -100%equal weight | 47-0.02 edge/pick |
| 0xdddc…daf6backed No | 63c | 69$43 in | Lost — open this pick on its own page | -$43.47 | 1 | 0%0 W · 1 L | -0.6wins | -0.63per pick | 63cpaid | -100%equal weight | 47-0.02 edge/pick |
| 0x4710…283cbacked No | 63c | 66$42 in | Lost — open this pick on its own page | -$41.58 | 1 | 0%0 W · 1 L | -0.6wins | -0.63per pick | 63cpaid | -100%equal weight | 47-0.02 edge/pick |
| 0x7026…482fbacked No | 63c | 66$42 in | Lost — open this pick on its own page | -$41.58 | 1 | 0%0 W · 1 L | -0.6wins | -0.63per pick | 63cpaid | -100%equal weight | 47-0.02 edge/pick |
| 0xe0dd…0ae2backed No | 63c | 65$41 in | Lost — open this pick on its own page | -$40.95 | 1 | 0%0 W · 1 L | -0.6wins | -0.63per pick | 63cpaid | -100%equal weight | 47-0.02 edge/pick |
| 0xef23…2a57backed No | 63c | 64$40 in | Lost — open this pick on its own page | -$40.32 | 1 | 0%0 W · 1 L | -0.6wins | -0.63per pick | 63cpaid | -100%equal weight | 47-0.02 edge/pick |
| 0x848d…871bbacked No | 63c | 62$39 in | Lost — open this pick on its own page | -$39.06 | 1 | 0%0 W · 1 L | -0.6wins | -0.63per pick | 63cpaid | -100%equal weight | 47-0.02 edge/pick |
| 0x2d0e…2a86backed No | 63c | 62$39 in | Lost — open this pick on its own page | -$39.06 | 1 | 0%0 W · 1 L | -0.6wins | -0.63per pick | 63cpaid | -100%equal weight | 47-0.02 edge/pick |
| 0xb80f…837bbacked No | 63c | 60$38 in | Lost — open this pick on its own page | -$37.8 | 1 | 0%0 W · 1 L | -0.6wins | -0.63per pick | 63cpaid | -100%equal weight | 47-0.02 edge/pick |
| 0x967e…7bfcbacked No | 63c | 60$38 in | Lost — open this pick on its own page | -$37.8 | 1 | 0%0 W · 1 L | -0.6wins | -0.63per pick | 63cpaid | -100%equal weight | 47-0.02 edge/pick |
| 0x7645…0fa8backed No | 63c | 58$37 in | Lost — open this pick on its own page | -$36.54 | 1 | 0%0 W · 1 L | -0.6wins | -0.63per pick | 63cpaid | -100%equal weight | 47-0.02 edge/pick |
| 0xeb56…1827backed No | 63c | 55$35 in | Lost — open this pick on its own page | -$34.65 | 1 | 0%0 W · 1 L | -0.6wins | -0.63per pick | 63cpaid | -100%equal weight | 47-0.02 edge/pick |
| 0x0711…f03cbacked No | 25c | 45$11 in | Lost — open this pick on its own page | -$11.2 | 193 | 37.3%72 W · 121 L | +9.0wins | +0.05per pick | 33cpaid | -10.4%equal weight | 55+0.04 edge/pick |
| 0x5669…0f13backed No | 56c | 34$19 in | Lost — open this pick on its own page | -$19.04 | 26 | 26.9%7 W · 19 L | -0.8wins | -0.03per pick | 30cpaid | -13.4%equal weight | 48-0.01 edge/pick |
| 0x0330…eb8fbacked No | 63c | 28$18 in | Lost — open this pick on its own page | -$17.64 | 24 | 33.3%8 W · 16 L | -0.7wins | -0.03per pick | 36cpaid | -36.6%equal weight | 48-0.01 edge/pick |
Entry is the average price this wallet paid on the side it backed, so being right at 20c is distinguishable from being right at 95c. Position is what it was left holding in shares, with what it spent underneath. Result opens that one pick on a page of its own, which is the link to send somebody. P/L held is what that position would have been worth held to resolution — not cash the wallet withdrew, because selling early is still a correct forecast. The seven columns on the right describe the wallet’s whole record in AI and say nothing about this market.
The rest of this event
Polymarket sells these questions together. 4 in all. TailMyPicks has no name for an event — the venue publishes an identifier and no title — so they are listed by their own questions.
- Will any OpenAI GPT model score at least 50% on the FrontierMath Exam?this page
- Will any OpenAI GPT model score at least 45% on the FrontierMath Exam?Yes won
- Will any OpenAI GPT model score at least 60% on the FrontierMath Exam?Yes won
- Will any OpenAI GPT model score at least 70% on the FrontierMath Exam?Yes won
Not every trade counts. A Pick has to clear four thresholds to be scored.
TailMyPicks scores a wallet on what it can actually be judged on: positions held to resolution, in markets with enough volume to be real, at prices where being right was not already priced in.
- The market traded at least $500.
- The entry price was between 0.00 and 0.80 — a near-certainty is not a call.
- The position was at least $10 — dust is not a position.
- The market has resolved, so there is a right answer to grade against.
Thresholds behind these numbers: set by an operator decision, not measured.