As of November 18, 2026, Polymarket prices “Will the highest score achieved by a Moonshot Kimi model on Humanity’s Last Exam in 2026 be 50% or higher?” at 10% YES with $53K traded. No tracked wallet holds a position on this market, so there is no verdict.
Kimi models already score above 50% on Humanity’s Last Exam, so a 2026 result of 50% or higher is very likely.
Moonshot AI's Kimi K3.1 Pro, released in late October 2026, posted a 52% score on Humanity's Last Exam, up from 47% for the prior K3 model, according to independent evaluations cited in launch coverage. The gain was smaller than improvements on other benchmarks such as SciCode, which rose from 59% to 61%, and CritPt physics, which moved from 23% to 25%. Analysts characterized the advance as stronger evidence of improved task execution than of a broad leap in reasoning capability, a distinction that matters for whether the highest score achieved by a Moonshot Kimi model on Humanity's Last Exam in 2026 will be 50% or higher. [VentureBeat, Oct 25]
Independent evaluator Artificial Analysis ranked K3.1 Pro fourth of 215 models on its Intelligence Index with a score of 55.1 as of October 23, 2026, trailing Claude Opus 5.5 at 57.6, Claude Sonnet 5.5 at 56.0, and Muse Wonder Full at 55.8. Moonshot described the release as its "most capable 3T-class open-weight model to date." The company's own comparisons put Kimi ahead of Opus on AutomationBench-AA, 73% to 70%, and on GDP.pdf document reasoning, 31% to 26%. The mixed benchmark picture leaves open whether the highest score achieved by a Moonshot Kimi model on Humanity's Last Exam in 2026 will be 50% or higher. [Medium, Oct 24]
The K3.1 Pro launch was overshadowed by allegations of a paid influencer scandal, which VentureBeat reported alongside the benchmark results. Moonshot has positioned the Kimi K3 family as a leading open-weight alternative to proprietary frontier models, with prior coverage tracking K3's benchmark and hallucination performance against rivals. Chinese AI models have been narrowing the performance gap with US counterparts while competing aggressively on cost per task, a dynamic that shapes how quickly Moonshot can push Kimi scores higher on difficult evaluations. Attention now turns to whether subsequent Kimi releases in 2026 can close the remaining gap to the 50% threshold on Humanity's Last Exam. [Klover.ai, Aug 31]
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 →