Will the highest score achieved by an Anthropic Claude model on Humanity’s Last Exam in 2026 be 60% or higher?
2 of 4 top Polymarket traders hold No (50%) · No at 69¢ · $3K held · ends Jan 1, 2027
⚖️
Neutral
No
4
No 50%
1 arb excluded
$2.7K
$190.25
49.6¢ → 68.5¢
+38% since entry · 2 traders
Research grade
NeutralNo at 69%
No measured edge, which here means a loss: the plain consensus (5+ holders, 60 %+, held to resolution) lost −3.0 % a trade after costs out of sample in the full-year test (n 86,296, 95 % CI −3.6 to −2.4 %).
- Consensus under 60 %Every backtest started at 60 %+ of the holders; below that nothing was measured.
- Favourite (60–95¢)Full year, out of sample: 0.70–0.90 lost −0.9 % a trade (n 26,050, 95 % CI −1.5 to −0.3): the least bad band, still a loss. The Oct 22 backtest's +0.4 % (n 4,327) was not confirmed.
The rules come from our Oct 22 2026 backtest (one entry per market, held to resolution, after a 1¢ half-spread and Polymarket's taker fees). Our full-year test without hindsight (Oct 26 2026) found none of them profitable out of sample, and the plain consensus lost −3.0 % a trade. The grade describes the market; it is not a forecast, not an edge and not advice.
Smart Money Signal
2 of 4 top traders (50%)1 arbitrage trader dimmed2 hold an outcome priced under 50%3 small positions dimmed (<$100 invested)
Outcome Probabilities
Smart Money Breakdown by Outcome
Signal Intelligence
Momentum
Flat
+0 pts consensus
Breadth
2 traders
Top 2 hold 100%
Freshness
Fresh
0h old
Flip Quality
Clean
0 consensus flips
50% of non-arb traders are on No. Concentration is driven by the top two positions owning 100% of that side's value.
| Trader | Position | Invested | Value | PnL | Record |
|---|---|---|---|---|---|
XT xtxpleasecallmeARB<$100 | Noavg 53.4¢ | $1.9K | $1.7K | +$103.77 | 36% 15095-27224 (42319) |
| └ No leg | Noavg 53.4¢ | $890.36 | $1.1K | +$216.4 | |
| └ Yes leg | Yesavg 40.8¢ | $725.33 | $586.17 | -$112.63 | |
 vinii | Noavg 49¢ | $663.2 | $866.8 | +$203.59 | 74% 2716-975 (3691) |
 Istaroth<$100 | Noavg 67¢ | $51 | $50 | -$1 | 23% 288-966 (1254) |
0X 0x2b670A311561DcAF741D8155451774D3Fa7fb814-1778467735876CTR<$100 | Yesavg 54.5¢ | $43.76 | $26.51 | -$14.05 | 45% 110-133 (243) |
 LornaPredictsCTR<$100 | Yesavg 39.9¢ | $35.9 | $12.6 | +$1.7 | 18% 520-2321 (2841) |
Invested
$1,888.56
Value
$1.7K
PnL
+$103.77
Record
36%
15095-27224 (42319)
Both legs:
viniiInvested
$663.2
Value
$866.8
PnL
+$203.59
Record
74%
2716-975 (3691)
Istaroth<$100Invested
$51
Value
$50
PnL
-$1
Record
23%
288-966 (1254)
Invested
$43.76
Value
$26.51
PnL
-$14.05
Record
45%
110-133 (243)
LornaPredictsCTR<$100Invested
$35.9
Value
$12.6
PnL
+$1.7
Record
18%
520-2321 (2841)
Chat
Sign in with your wallet to post.
EV Calculator
Consensus % is how many tracked traders hold a side, not a win probability.
68.5¢ price + 1.0¢ spread + 0.8¢ fee (Tech 4%). Win more often than this and the bet pays.
A market order pays the taker fee and crosses the spread (assumed 1.0¢); a limit order pays no fee but may not fill. The fee category is a guess from the title.