Highest OpenAI score on Humanity’s Last Exam in 2026?

$83.1K Vol
2027年1月1日
Active
概率趋势
50%+ 95.7%
55%+ 73.5%
60%+ 39.5%
65%+ 21.0%
70%+ 10.5%

核心摘要

根据「Highest OpenAI score on Humanity’s Last Exam in 2026?」的最新预测市场数据,交易者已形成强烈共识。

目前,50%+ 以压倒性的 93.8% 获胜概率主导市场;55%+ 以 72.5% 位居第二,60%+ 以 39.5% 排名第三。该市场的下注量已达 $83.1K,反映出市场的高度关注。

竞争梯队拆解

为了更好地评估各潜在结果的位置,可依据隐含概率与合约定价将市场划分为三个明显的交易梯队:

🥇 第一梯队:绝对领跑者

  • 50%+ (93.8%):50%+ 目前拥有最高概率,深受订单簿青睐。看好该结果的交易者面对的「Buy Yes」合约价为 94¢,显示出市场的高度确信。仅该合约就已产生 $13.8K 的成交量。

🥈 第二梯队:主要挑战者

  • 55%+ (72.5%):作为最可行的替代选项,55%+ 保持着 72.5% 的成真概率,其「Buy Yes」份额目前成交价为 73¢。
  • 60%+ (39.5%):以 39.5% 的概率位列第三,市场对 60%+ 持谨慎怀疑态度,除非势头转变,否则视其为外围黑马。

完整订单簿与定价面板

下表列出了该预测池中所有结果的合约价格、概率与市场深度的完整拆解:

排名预测结果获胜概率成交量买入 Yes(成本)买入 No(成本)
150%+93.8%$13.8K94¢
255%+72.5%$31.8K73¢28¢
360%+39.5%$26.5K40¢61¢

裁决规则

This market will resolve to "Yes" if any model published by OpenAI achieves at least the specified accuracy on Humanity’s Last Exam by December 31, 2026, 11:59 PM ET. Otherwise, this market will resolve to "No".

For resolution, “accuracy” refers solely to the value labeled “HLE Accuracy” or a clear equivalent metric if the data’s presentation or terminology is restructured, regardless of the model’s Calibration Error or any other displayed metric.

The resolution source will be the official Humanity’s Last Exam leaderboard at https://agi.safe.ai/. If the resolution source becomes unavailable during the listed timeframe, this market will remain open to allow the relevant data to become available again. If the source remains unavailable after the end of the listed timeframe or is otherwise confirmed to be permanently unavailable, official Humanity’s Last Exam results published elsewhere may be used. If no official alternative source is available, this market will resolve to "No".

AI 估值分析:发现市场错误定价与 EV 差

人群共识与投机成交塑造了更宏观的预测市场,而我们的量化算法提供了数据驱动的反向视角。通过分析基本面信号、底层趋势与历史分布,我们的 AI 估值模型为每个结果独立测算出一个「公允价值」概率。

将该公允价值与当前交易价值对比,可揭示出重大背离——即期望值(EV)差。正 EV 差代表统计上被低估的结果,而负 EV 差则提示市场可能存在反应过度。

顶级 AI Alpha 与错误定价套利机会

根据最新一轮数据模型测算,以下几个关键合约存在显著偏离:

  • 最被高估的结果:50%+ 当前交易价为 93.8%,但我们的 AI 测算其公允价值仅为 82.3%,形成 -11.5% 的较大负 EV 差,表明人群可能过度炒作该结果、把溢价推得过高。
  • 最佳价值标的(最高 EV):我们的模型将 55%+ 识别为盘面上最具价值的机会。市场仅给予其 72.5% 的交易概率,而我们 AI 的公允价值评估为 77.9%——形成可观的 +5.4% EV 差。
MarketTrade ValueFair ValueEV Gap
50%+93.8%82.3%-11.5%
55%+Best EV72.5%77.9%+5.4%
60%+39.5%36.4%-3.1%

交易动态

以下是该事件的交易动态。

Sep 8, 2026

  • 07:31 AM
    0X0xDbBc0a6D4d1490ADA6f08572D31a3CebdB3Cc072-1788224806798
    $24.84

    Sold 92 No for Will the highest score achieved by an OpenAI model on Humanity’s Last Exam in 2026 be 55% or higher? at 0.27

  • 06:13 AM
    PRpragmat1sm
    $146.00

    Bought 200 Yes for Will the highest score achieved by an OpenAI model on Humanity’s Last Exam in 2026 be 55% or higher? at 0.73

  • 06:03 AM
    CYcybermaxs
    $18.00

    Sold 30 No for Will the highest score achieved by an OpenAI model on Humanity’s Last Exam in 2026 be 60% or higher? at 0.6

  • 05:33 AM
    COComputerdude111
    $4.75

    Bought 5 Yes for Will the highest score achieved by an OpenAI model on Humanity’s Last Exam in 2026 be 50% or higher? at 0.95

  • 05:32 AM
    COComputerdude111
    $85.73

    Sold 317.51 No for Will the highest score achieved by an OpenAI model on Humanity’s Last Exam in 2026 be 55% or higher? at 0.27

  • 05:02 AM
    RURushmore98
    $1.00

    Bought 1.369864 Yes for Will the highest score achieved by an OpenAI model on Humanity’s Last Exam in 2026 be 55% or higher? at 0.73

  • 03:39 AM
    PRpragmat1sm
    $7.20

    Bought 10 Yes for Will the highest score achieved by an OpenAI model on Humanity’s Last Exam in 2026 be 55% or higher? at 0.72

  • 03:37 AM
    COComputerdude111
    $48.80

    Sold 80 No for Will the highest score achieved by an OpenAI model on Humanity’s Last Exam in 2026 be 60% or higher? at 0.61

  • 03:35 AM
    COComputerdude111
    $24.36

    Sold 84 No for Will the highest score achieved by an OpenAI model on Humanity’s Last Exam in 2026 be 55% or higher? at 0.29

  • 02:58 AM
    LOLovelyPanda
    $7.00

    Sold 33.32 Yes for Will the highest score achieved by an OpenAI model on Humanity’s Last Exam in 2026 be 65% or higher? at 0.21

  • 02:56 AM
    BIbig-bird1
    $1.80

    Bought 1.892166 Yes for Will the highest score achieved by an OpenAI model on Humanity’s Last Exam in 2026 be 50% or higher? at 0.95

  • 02:56 AM
    WEwendywu1
    $43.70

    Bought 46 Yes for Will the highest score achieved by an OpenAI model on Humanity’s Last Exam in 2026 be 50% or higher? at 0.95

正在押注该事件的鲸鱼钱包

FO1
folioquant
事件盈亏
-$128.69
成交量
$6,364.96
持仓数
YesYesYes+4
OL2
Olcan
事件盈亏
+$217.53
成交量
$4,321.23
持仓数
NoNoNo+2
PR3
pragmat1sm
事件盈亏
+$21.83
成交量
$3,244.87
持仓数
YesYesYes+4
ST4
SteviaDaddy
事件盈亏
+$12.99
成交量
$1,983.35
持仓数
NoNoNo+3
WE5
wendywu1
事件盈亏
+$57.85
成交量
$814.95
持仓数
YesYesNo+2
DR6
Dr.PNL
事件盈亏
-$105.47
成交量
$802.81
持仓数
NoNoNo
IU7
iutwpfal
事件盈亏
+$155.44
成交量
$763.08
持仓数
YesYesNo+1
LO8
LornaPredicts
事件盈亏
-$89.22
成交量
$717.19
持仓数
NoNoNo+4

常见问题

当前市场对「Highest OpenAI score on Humanity’s Last Exam in 2026?」的共识是什么?

截至最新更新,50%+ 以 93.8% 的获胜概率领跑,其次是 55%+(72.5%),以及 60%+(39.5%)。该市场总成交量已达 $83.1K,显示出充足的流动性与高交易参与度。

AI 公允价值与实时市场交易价值有何不同?

实时市场交易价值反映的是公众情绪、订单簿动能与投机资金。我们的 AI 公允价值则由量化模型独立计算,剔除情绪炒作、专注底层数据。两者出现显著背离时即形成 EV 差,提示市场对某个结果可能存在错误定价。

当前哪个结果的期望值(EV)最高?

最新一轮测算显示,55%+ 是最显著的错误定价。市场对其隐含概率仅给到 72.5%,而我们的 AI 测算其公允价值为 77.9%——形成 +5.4% 的期望值差,是该市场中最具价值的标的。

市场共识是否对某个结果反应过度?

是的——数据显示市场对 50%+ 存在明显的反应过度。人群把其实时交易价值推高至 93.8%,但我们的公允价值评估认为其真实概率仅为 82.3%,形成 -11.5% 的负 EV 差,表明该合约被高估。

免费开始