D2VBench - Civilizational Progress: leaderboard

Metric: Value-alignment score (0-100) on the civilizational-progress scenarios; 10,000 everyday value-dilemma scenarios answered free-form; GLM-4.6 and Qwen3-Max map each response to the matching options and score its coverage of annotated interpretability points over five dimensions (0-100), the two judges averaged. Source: arxiv.org. Saturation forecast: Around August 2027. 8 models tracked.

Top models

#ModelScore
1GPT-5.164.1
2Gemini 3 Pro (Preview)61.18
3DeepSeek R1 052859.36
4MiniMax-M258.14
5GLM-4.658.06
6Claude Haiku 4.5 (20251001)56.34
7Kimi K2 090555.72
8Seed-1.654.03

Interactive version: theaggregate.ai/benchmark?slug=d2vbench-civilizational-progress · How It Works · Data refreshed daily, snapshot 2026-09-29.