TopBench (Agentic) - Ranking (NDCG): leaderboard
TopBench (2026) tests implicit predictive reasoning in table question answering: the answer is not in the table and must be predicted from historical rows. NDCG from 0 to 1 of the ranked records the agent writes to a CSV file for ranking questions, solved by an agent that runs Python in a sandbox; higher is better.
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 February 2027. 8 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 0.5 | #261 |
| 2 | Gemini 3 Flash | 0.5 | #175 |
| 3 | DeepSeek V3.2 | 0.5 | #419 |
| 4 | GPT-5.2 | 0.41 | #185 |
| 5 | Qwen 3 235B A22B 2507 (Thinking) | 0.41 | #466 |
| 6 | Qwen 3 235B A22B 2507 Instruct | 0.28 | #616 |
| 7 | TableLLM-8B | 0 | |
| 8 | TableLLM-13B | 0 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=topbench-agentic-ranking-ndcg · How It Works · Data refreshed daily, snapshot 2026-11-21.