Kimi K3.1 Pro Tech Blog - HLE-Full (text-only subset): leaderboard

Moonshot KimiK3.1Pro release evaluations; explicit max header, Kimi temperature1/top-p0.95 except specified overrides. GLM text-only subset of the 2,500-question full set; subset size unstated. No full-set denominator is assigned. Score (%). Copied third-party comparator results are not re-ingested; source-specific harness retained.

Metric: Score (%). Source: www.kimi.com. 1 models tracked.

Top models

#ModelScoreOverall rank
1GLM-5.3 (max)43#37 (GLM-5.3)

Interactive version: theaggregate.ai/benchmark?slug=kimi-k3-1-pro-tech-blog-hle-full-text-only-subset · How It Works · Data refreshed daily, snapshot 2026-10-24.