Triplet Incremental Training Study - NuInstruct mAP: leaderboard
Triplet Incremental Training v1: unchanged zero-shot InternVL3.5-4B on the source native driving-language panel; exact inference prompt/toolkit/score normalization not reported. No SFT Baseline/Ours score is assigned to this checkpoint. Source singleton measurements remain evidence; no ranking eligibility is inferred. Metric: Native mAP (%) Higher is better.
Metric: Native mAP (%). Source: arxiv.org. 1 model tracked. Updated 14 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | InternVL3.5-4B | 0 | #1916 |
Interactive version: theaggregate.ai/benchmark?slug=triplet-incremental-training-study-nuinstruct-map · How It Works · Data refreshed daily, snapshot 2026-11-16.