DiVR - MBPP: leaderboard
DiVR v1 released unmodified generators only, under native Greedy, Confidence-guided and ReMDM resampling conditions. Canvas 256 tokens except MATH-500 512; 64 inference steps, dataset-specific native evaluation. DiVR-guided and DiVR best-of-four require trained LoRA+MLP verifiers without affirmative public weight artifacts and are retained in the independent source-identity hold packet, never attributed to the frozen generator. Base and Instruct checkpoints stay distinct. Native source table scores/conditions retained. Held DiVR guided configurations use at most three regenerations, theta0.5 and4alternatives attemperature0.7; these trained-verifier settings are not assigned to the retained frozen-generator baselines. Metric: Native task accuracy (%)..
Metric: Native task accuracy (%).. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 7 models tracked. Updated 14 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Dream-v0-Instruct-7B (Harness: DiVR SR-SMC (4)) | 50.2 | |
| 2 | Dream-v0-Instruct-7B (Harness: DiVR Prism) | 46.4 | |
| 3 | Dream-v0-Instruct-7B (Harness: DiVR Greedy) | 43.8 | |
| 4 | LLaDA-8B-Instruct (Harness: DiVR SR-SMC (4)) | 34 | |
| 5 | LLaDA-8B-Instruct (Harness: DiVR Greedy) | 33.2 | |
| 6 | LLaDA-8B-Instruct (Harness: DiVR Prism) | 31.6 | |
| 7 | LLaDA-8B-Base (Harness: DiVR Greedy) | 30.2 |
Interactive version: theaggregate.ai/benchmark?slug=divr-mbpp · How It Works · Data refreshed daily, snapshot 2026-11-16.