Highest score on Humanity’s Last Exam in 2026?
- Will the highest score achieved on Humanity’s Last Exam in 2026 be 60% or higher?55¢
- Will the highest score achieved on Humanity’s Last Exam in 2026 be 65% or higher?28¢
- Will the highest score achieved on Humanity’s Last Exam in 2026 be 70% or higher?16¢
- Will the highest score achieved on Humanity’s Last Exam in 2026 be 75% or higher?10¢
- Will the highest score achieved on Humanity’s Last Exam in 2026 be 80% or higher?8¢
- Will the highest score achieved on Humanity’s Last Exam in 2026 be 90% or higher?8¢
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".
Anthropic's Claude models currently lead the Humanity's Last Exam leaderboard with top scores near 55-65% as of mid-August 2026, reflecting steady gains in expert-level reasoning across math, sciences, and humanities. The benchmark's 2,500 graduate-level questions, released publicly in early 2026 with a private holdout set, were designed to avoid rapid saturation seen in prior tests. Competitive pressure from OpenAI, Google DeepMind, and others has driven iterative improvements in chain-of-thought techniques, adaptive reasoning modes, and model scale since initial single-digit results in 2025. Key catalysts ahead include potential new frontier releases, refined evaluation methods, and any breakthroughs in multi-modal or agentic capabilities before year-end resolution.