ELBench - High-Level Cultivation: leaderboard

Metric: Module score (%; mean per-item score on 1,000 synthesized items: 500 structured pedagogical-judgement choices and 500 open-ended educational generations judged against a reference; zero-shot, temperature 0; open-ended items scored by a Qwen3.6 rubric judge, majority of 9 calls). Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.

Top models

#ModelScore
1Gemini 3.5 Flash75.3
2GPT-5.475.1
3GLM-5.175
4Seed 2.0 Pro73.5
5DeepSeek V4 Flash71.5
6DeepSeek V4 Pro69.5
7Claude Opus 4.869.5

Interactive version: theaggregate.ai/benchmark?slug=elbench-high-level-cultivation · How It Works · Data refreshed daily, snapshot 2026-09-29.