TopBench (Agentic) - Ranking (NDCG): leaderboard
Metric: NDCG (0 to 1) on TopBench's ranking questions with regression targets, solved by the authors' ReAct agent that writes and runs Python in a Docker sandbox over the table: the agent writes a CSV of the records that meet the stated filter, ranked by their predicted outcome, scored against the reference ranking; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 0.5 |
| 2 | Gemini 3 Flash | 0.5 |
| 3 | DeepSeek V3.2 | 0.5 |
| 4 | DeepSeek V3.2 (Thinking) | 0.46 |
| 5 | GPT-5.2 | 0.41 |
| 6 | Qwen 3 235B A22B 2507 (Thinking) | 0.41 |
| 7 | Qwen 3 235B A22B 2507 Instruct | 0.28 |
Interactive version: theaggregate.ai/benchmark?slug=topbench-agentic-ranking-ndcg · How It Works · Data refreshed daily, snapshot 2026-10-07.