As of November 16, 2026, Polymarket prices “Will the highest score achieved by a SpaceXAI Grok model on Humanity’s Last Exam in 2026 be 45% or higher?” at 63% YES with $69K traded. No tracked wallet holds a position on this market, so there is no verdict.
Prediction markets put the probability at 54%: Will the highest score achieved by a SpaceXAI Grok model on Humanity’s Last Exam in 2026 be 45% or higher. Currently, markets are divided (54% YES, 46% NO). Google’s slow slide on the closely watched Artificial Analysis Intelligence Index has reached a new low.
SpaceXAI released Grok 4.7 on September 21, 2026, a closed flagship model priced at $2 per million input tokens and $6 per million output tokens. On the current Artificial Analysis Intelligence Index (version v4.3.2), Grok 4.7 scored 46, one point ahead of Qwen 3.8 Max at 45, which was released August 3, 2026 and refreshed on September 2, 2026. The index aggregates ten evaluations, including Humanity's Last Exam, the benchmark central to the question of whether the highest score achieved by a SpaceXAI Grok model on Humanity's Last Exam in 2026 will be 45% or higher. The near-identical pricing and benchmark positioning of the two models underscores how tightly contested the frontier has become. [Orcarouter, Sep 21]
The same index snapshot showed Google falling to tenth place among AI labs, with its best-ranked model, Gemini 3.8 Flash, sitting 14th at a score of 41 — well behind the leading pack. Because Humanity's Last Exam is one of the ten constituent evaluations, movements on the composite index offer a partial signal of lab performance on the exam itself, though the two metrics are not identical. The gap between Grok 4.7's composite score of 46 and Gemini 3.8 Flash's 41 places SpaceXAI ahead of Google in the current rankings, a reversal from earlier cycles. Whether that lead translates into a Humanity's Last Exam result at or above the 45% threshold remains the open question. [Officechai, Sep 22]
SpaceXAI, legally X.AI LLC, is headquartered in Palo Alto, California, and operates as a privately held subsidiary of Space Exploration Technologies Corp., with a B2B and B2C business model. The company's Grok line has expanded rapidly through 2026, and the September 21 launch of Grok 4.7 marked its latest flagship release. Attention now turns to independent benchmark reporting for the model on Humanity's Last Exam specifically, since composite index scores do not disclose per-evaluation results. The outcome will determine whether the highest score achieved by a SpaceXAI Grok model on Humanity's Last Exam in 2026 clears the 45% mark. [SpaceXAI, recent]
None of the 166 tracked wallets holds a position here, so the Radar makes no call — price, volume and news above are live. When a tracked wallet takes a position, this page gets a verdict.
See the markets with a verdict →