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
| # | Model | Score |
|---|---|---|
| 1 | Kimi K3 | 56.12 |
| 2 | GPT-5.6 Sol | 55.36 |
| 3 | Qwen 3.8 Max (0902) | 51.21 |
| 4 | GLM-5.2 | 48.58 |
| 5 | DeepSeek V4 Pro | 36.22 |
Interactive version: theaggregate.ai/benchmark?slug=longds-v1-1-full-social-good · How It Works · Data refreshed daily, snapshot 2026-09-25.