Ambig-DS - Objective (Ambiguous): leaderboard
Metric: Normalized task score (0-100) in the Ambiguous condition (no clarification channel) on the 61 objective-ambiguity tasks of Ambig-DS (MLE-bench competitions whose prompt and data no longer fix the evaluation metric), scored by the original MLE-bench grader against the Kaggle median and normalized to 0-1 (times 100, so 0-100; invalid and timed-out runs score 0), code agents in the OpenCode harness with a 24-hour budget; higher is better. Source: arxiv.org. Saturation forecast: Around September 2028. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 23 |
| 2 | Claude Haiku 4.5 | 23 |
| 3 | GPT-5.4 | 22 |
| 4 | Gemini 3 Flash | 22 |
| 5 | GPT-5.4 Nano | 5 |
Interactive version: theaggregate.ai/benchmark?slug=ambig-ds-objective-ambiguous · How It Works · Data refreshed daily, snapshot 2026-10-07.