TopBench (Agentic) - Treatment Effect: leaderboard
Metric: Trend accuracy (0 to 1) on TopBench's 105 treatment-effect questions, which ask whether a counterfactual change to a profile raises or lowers its outcome given a historical table, solved by the authors' ReAct agent that writes and runs Python in a Docker sandbox over the table: share of questions whose predicted direction matches the reference; values and decisions extracted from the free-text answer by a DeepSeek-V3.2 judge and checked against the answer text; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 0.65 |
| 2 | Gemini 3 Flash | 0.65 |
| 3 | DeepSeek V3.2 (Thinking) | 0.65 |
| 4 | Claude Sonnet 4.5 | 0.63 |
| 5 | DeepSeek V3.2 | 0.57 |
| 6 | Qwen 3 235B A22B 2507 Instruct | 0.53 |
| 7 | Qwen 3 235B A22B 2507 (Thinking) | 0.53 |
Interactive version: theaggregate.ai/benchmark?slug=topbench-agentic-treatment-effect · How It Works · Data refreshed daily, snapshot 2026-10-07.