MemCalib: leaderboard
Metric: Sample Calibration Score (%; geometric-decay score over per-response memory over-use and under-use totals, DeepSeek-V4-Pro rubric judge, mean over 3 seeds; non-thinking mode). Source: arxiv.org. Saturation forecast: Around 2030. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol (Non-reasoning) | 46.25 |
| 2 | Claude Sonnet 4.6 | 36.44 |
| 3 | Kimi K2.6 (Non-reasoning) | 35.54 |
| 4 | GLM-5.2 (Non-reasoning) | 34.4 |
| 5 | DeepSeek V4 Flash (Non-reasoning) | 33.72 |
| 6 | Qwen 3 8B (Non-reasoning) | 31.17 |
| 7 | Qwen 3.5 35B A3B (Non-reasoning) | 26.54 |
Interactive version: theaggregate.ai/benchmark?slug=memcalib · How It Works · Data refreshed daily, snapshot 2026-09-26.