ToxReason - Causal Coherence: 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. Whether the explanation follows a consistent causal chain from initiating events to outcomes, scored 0 to 10 by a Claude Sonnet 4.5 judge; higher is better.

Metric: Causal coherence (0-10) of the mechanistic explanation from initiating events through key events to adverse outcomes, 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 December 2027. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-5.15.88#240
2GPT-55.79#178
3O35.74#237
4O4 Mini5.55#368
5Gemma 3 27B (IT)5.33#1324
6GPT-4o5.24#751
7Qwen 3 4B Instruct4.97#1696
8Llama 3.1 70B Instruct4.87#1571
9Qwen 2.5 14B Instruct4.77#1775
10DeepSeek R1 Distill Llama 70B4.68#1669
11Llama 3.1 8B Instruct3.69#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-causal-coherence · How It Works · Data refreshed daily, snapshot 2026-11-21.