TopBench (Agentic) - Decision Making: leaderboard
Metric: Decision accuracy (0 to 1) on TopBench's 186 decision-making questions, which ask which of several described profiles will have the best predicted 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 final choice 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 | Gemini 3 Flash | 0.65 |
| 2 | DeepSeek V3.2 | 0.59 |
| 3 | DeepSeek V3.2 (Thinking) | 0.58 |
| 4 | Qwen 3 235B A22B 2507 (Thinking) | 0.57 |
| 5 | Claude Sonnet 4.5 | 0.56 |
| 6 | GPT-5.2 | 0.55 |
| 7 | Qwen 3 235B A22B 2507 Instruct | 0.45 |
Interactive version: theaggregate.ai/benchmark?slug=topbench-agentic-decision-making · How It Works · Data refreshed daily, snapshot 2026-10-07.