LongDS v1.1 Full - Education: leaderboard
Metric: Accuracy (%; judged turn accuracy macro-averaged over 8 tasks), each model under one agentic coding harness. Source: zjunlp.github.io. Saturation forecast: Around December 2026. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 93.87 |
| 2 | GLM-5.2 | 88.91 |
| 3 | Qwen 3.8 Max (0902) | 88.88 |
| 4 | Kimi K3 | 82.2 |
| 5 | DeepSeek V4 Pro | 72.95 |
Interactive version: theaggregate.ai/benchmark?slug=longds-v1-1-full-education · How It Works · Data refreshed daily, snapshot 2026-09-25.