SupraBench - Binding Affinity MAE (CoT): leaderboard

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 June 2027. 8 models tracked.

Top models

#ModelScore
1Gemini 3 Flash1.26
2Llama 3.1 70B Instruct1.83
3GPT-5.4 Mini2.04
4GPT-5.4 Nano2.16
5Qwen 3.5 27B2.44
6Qwen 3.5 9B3.66
7Llama 3.1 8B Instruct4.91

Interactive version: theaggregate.ai/benchmark?slug=suprabench-binding-affinity-mae-cot · How It Works · Data refreshed daily, snapshot 2026-09-29.