- 2026'daki İnsanlığın Son Sınavı'nda elde edilen en yüksek puan %58 veya daha yüksek olacak mı?97¢%97
- 2026'daki İnsanlığın Son Sınavı'nda elde edilen en yüksek puan %60 veya daha yüksek olacak mı?88¢%88
- 2026’daki İnsanlığın Son Sınavı’nda elde edilen en yüksek puan %65 veya daha yüksek olacak mı?47¢%47
- İnsanlığın Son Sınavı'nda 2026'da elde edilen en yüksek puan %70 veya daha yüksek olacak mı?14¢%14
- 2026'daki İnsanlığın Son Sınavı'nda elde edilen en yüksek puan %75 veya daha yüksek olacak mı?6¢%6
- 2026'daki İnsanlığın Son Sınavı'nda elde edilen en yüksek puan %80 veya daha yüksek olacak mı?2¢%2
- 2026 yılında İnsanlığın Son Sınavı'nda elde edilen en yüksek puan %90 veya daha yüksek olacak mı?2¢%2
- %7%9758%+$6,9 B hacim
- %29%8860%+$80,6 B hacim
- %20%4765%+$40 B hacim
- %5%1470%+$11,2 B hacim
- %1%5,675%+$6,4 B hacim
- %2,180%+$2,6 B hacim
- %2,290%+$3,6 B hacim
Recent leaderboard updates as of November 2026 show Moonshot AI’s Kimi K3.1 Pro leading Humanity’s Last Exam at 70% on tool-augmented runs, ahead of Anthropic’s Claude Opus 5.5 and Fable 5.1 variants near 65%. These gains reflect iterative improvements in large language model reasoning, agentic tool integration, and refined training on expert-level academic questions across the 2,500-item benchmark. Earlier 2026 results hovered in the mid-50% range before tool-use evaluations and model scaling produced sharper jumps. Frontier labs including OpenAI, Google, and Meta continue releasing updated systems ahead of year-end, with competitive pressure on capability benchmarks like HLE-Diamond driving further gains. Trader sentiment tracks these official releases and independent evaluations closely, as the highest verified score by December 31 will determine resolution.
Kurallar
This market will resolve to "Yes" if any model 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".