ToxReason - Pathway Alignment: leaderboard
Metric: Needleman-Wunsch alignment score (0-1) between the model's reasoning steps and the reference adverse outcome pathway steps, combining semantic similarity and causal order, 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 2033. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 | 0.51 |
| 2 | Gemma 3 27B (IT) | 0.5 |
| 3 | GPT-4o | 0.49 |
| 4 | O3 | 0.49 |
| 5 | O4 Mini | 0.49 |
| 6 | Qwen 2.5 14B Instruct | 0.48 |
| 7 | Qwen 3 4B Instruct | 0.48 |
| 8 | GPT-5 | 0.48 |
| 9 | Llama 3.1 70B Instruct | 0.47 |
| 10 | DeepSeek R1 Distill Llama 70B | 0.46 |
| 11 | Llama 3.1 8B Instruct | 0.4 |
Interactive version: theaggregate.ai/benchmark?slug=toxreason-pathway-alignment · How It Works · Data refreshed daily, snapshot 2026-10-07.