ToxReason - Mechanistic Reasoning: leaderboard

ToxReason (2026) tests mechanistic chemical toxicity reasoning: given a query molecule with experimental initiating-event evidence from structurally similar compounds, the model predicts liver, heart and kidney toxicity and explains how molecular initiating events lead to the adverse outcome along an Adverse Outcome Pathway. Overall quality of the mechanistic explanation, scored 0 to 10 by a Claude Sonnet 4.5 judge against the reference pathway; higher is better.

Metric: Overall quality (0-10) of the step-wise mechanistic explanation linking molecular initiating events to the organ-level adverse outcome, scored 0 to 10 by a Claude Sonnet 4.5 judge against the reference adverse outcome pathway, on the ToxReason test set (query chemicals with curated human CTD toxicity labels and adverse outcome pathway context, eight retrieved activation and inhibition examples from similar compounds), zero-shot, temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Around May 2028. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-5.15.52#240
2GPT-55.42#178
3O35.33#237
4GPT-4o4.96#751
5Gemma 3 27B (IT)4.96#1324
6O4 Mini4.95#368
7Llama 3.1 70B Instruct4.65#1571
8Qwen 2.5 14B Instruct4.53#1775
9Qwen 3 4B Instruct4.52#1696
10DeepSeek R1 Distill Llama 70B4.49#1669
11Llama 3.1 8B Instruct3.28#4600

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=toxreason-mechanistic-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.