- Will the highest score achieved by a Google Gemini model on Humanity’s Last Exam in 2026 be 50% or higher?71¢
- Will the highest score achieved by a Google Gemini model on Humanity’s Last Exam in 2026 be 55% or higher?51¢
- Will the highest score achieved by a Google Gemini model on Humanity’s Last Exam in 2026 be 60% or higher?32¢
- Will the highest score achieved by a Google Gemini model on Humanity’s Last Exam in 2026 be 65% or higher?14¢
- Will the highest score achieved by a Google Gemini model on Humanity’s Last Exam in 2026 be 70% or higher?6¢
This market will resolve to "Yes" if any Google Gemini 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".
Google’s latest Gemini 3.x models, including 3.1 Pro and 3.7 Flash variants, have posted Humanity’s Last Exam scores in the mid-to-high 40s percent as of August 2026, trailing Anthropic’s Claude Opus 5 (55–65 percent range) and select GPT-5 configurations on the leading public leaderboards. Rapid gains in chain-of-thought reasoning and multi-step problem solving across the frontier explain the overall upward trajectory since the benchmark’s launch, yet Gemini has not yet closed the gap on the hardest knowledge and reasoning items that define HLE resolution. Traders are watching Google DeepMind’s cadence of model releases, potential Gemini 4 previews, and any internal reasoning optimizations for the remainder of the year, as further gains of 8–15 points would be needed to push the highest Gemini score across common market thresholds before December 31.