TopBench - Single-Point Prediction: leaderboard
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, answered from the serialized table (header kept, rows randomly sampled when it exceeds the context budget) without tools: 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 January 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 0.65 |
| 2 | DeepSeek V3.2 | 0.59 |
| 3 | Qwen 3 235B A22B 2507 Instruct | 0.57 |
| 4 | DeepSeek V3.2 (Thinking) | 0.57 |
| 5 | GPT-5.2 | 0.55 |
| 6 | Qwen 3 235B A22B 2507 (Thinking) | 0.44 |
Interactive version: theaggregate.ai/benchmark?slug=topbench-single-point-prediction · How It Works · Data refreshed daily, snapshot 2026-10-07.