Ambig-DS - Target (Ambiguous): leaderboard
Metric: Normalized task score (0-100) in the Ambiguous condition (no clarification channel) on the 51 target-ambiguity tasks of Ambig-DS (DSBench data-modeling tasks whose prompt and data no longer fix the prediction target), scored by the original DSBench evaluator as the relative performance gap normalized to 0-1 (times 100, so 0-100; invalid and timed-out runs score 0), code agents in the OpenCode harness with a 2-hour budget; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 49 |
| 2 | Gemini 3 Flash | 44 |
| 3 | GPT-5.4 Nano | 39 |
| 4 | GPT-5.4 | 32 |
| 5 | Claude Haiku 4.5 | 32 |
Interactive version: theaggregate.ai/benchmark?slug=ambig-ds-target-ambiguous · How It Works · Data refreshed daily, snapshot 2026-10-07.