TopBench (Agentic) - Single-Point Prediction: 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. Prediction accuracy from 0 to 1 on single-point questions, solved by an agent that runs Python in a sandbox; higher is better.

Metric: Prediction accuracy (0 to 1) on TopBench's 274 single-point questions, which ask for an unobserved outcome of a profile given a historical table, solved by the authors' ReAct agent that writes and runs Python in a Docker sandbox over the table: a regression answer earns 0.6 x (1 - range-normalized absolute error) plus 0.4 x the overlap of its predicted interval with the reference interval, penalized when the interval is too wide, and a classification answer earns credit for the right class; 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 February 2027. 8 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 3 Flash0.66#175
2Claude Sonnet 4.50.64#261
3DeepSeek V3.2Thinking0.61#419
4GPT-5.20.6#185
5Qwen 3 235B A22B 2507 (Thinking)0.57#466
6Qwen 3 235B A22B 2507 Instruct0.43#616
7TableLLM-13B0.12
8TableLLM-8B0.1

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-single-point-prediction · How It Works · Data refreshed daily, snapshot 2026-11-21.