LongDS v1.1 Full - Social Good: leaderboard

Metric: Accuracy (%; judged turn accuracy macro-averaged over 10 tasks), each model under one agentic coding harness. Source: zjunlp.github.io. Saturation forecast: Around October 2027. 6 models tracked.

Top models

#ModelScore
1Kimi K356.12
2GPT-5.6 Sol55.36
3Qwen 3.8 Max (0902)51.21
4GLM-5.248.58
5DeepSeek V4 Pro36.22

Interactive version: theaggregate.ai/benchmark?slug=longds-v1-1-full-social-good · How It Works · Data refreshed daily, snapshot 2026-09-25.