SupraBench - Binding Affinity MAE (CoT): leaderboard
SupraBench (2026) tests LLMs on supramolecular host-guest chemistry built with domain experts. This board is the mean absolute error of the predicted binding affinity (log Ka) under standard aqueous conditions, with a chain-of-thought prompt; lower is better.
Metric: Mean absolute error of the predicted log Ka of host-guest binding under standard aqueous conditions (2,609 records), chain-of-thought prompt (explicit reasoning before the answer); lower is better. Source: arxiv.org. Saturation forecast: Around May 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 1.26 | #164 |
| 2 | Llama 3.1 70B Instruct | 1.83 | #1546 |
| 3 | GPT-5.4 Mini | 2.04 | #389 |
| 4 | GPT-5.4 Nano | 2.16 | #635 |
| 5 | Qwen 3.5 27B | 2.44 | #359 |
| 6 | Qwen 3.5 9B | 3.66 | #803 |
| 7 | Llama 3.1 8B Instruct | 4.91 | #4246 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=suprabench-binding-affinity-mae-cot · How It Works · Data refreshed daily, snapshot 2026-11-13.