Contamination Map Methodology

Text / LLM / Model

LLaVA-OneVision-1.5

Organisation
LLaVA-OneVision Community Contributors (EvolvingLMMs-Lab)
Family
LLaVA · version 1.5
Released
2025-09-28 (arXiv v1 submission date (2509.23661); HF repo lmms-lab/LLaVA-OneVision-1.5-8B-Instruct created 2025-09-16)
Checkpoints
lmms-lab/LLaVA-OneVision-1.5-4B-Instruct, lmms-lab/LLaVA-OneVision-1.5-8B-Instruct, lmms-lab/LLaVA-OneVision-1.5-4B-Base, lmms-lab/LLaVA-OneVision-1.5-8B-Base
Weights
Open · Apache 2.0
Links
PaperModel cardCode

Training data disclosure: Partial list

Level determined for 18% of benchmark cells.

“a meticulously curated 22M instruction dataset LLaVA-OneVision-1.5-Instruct”
arxiv.org · paper · Abstract · retrieved 2026-10-15
“As part of the LLaVA-OneVision-1.5 open-source initiative, we are releasing this dataset to the community”
huggingface.co · dataset card · Introduction · retrieved 2026-10-15

Built on

Everything these base models may have seen is inherited by LLaVA-OneVision-1.5.

Other declared training data

Benchmark cells

Classic LLM benchmarks

Unknown MMLU (Measuring Massive Multitask Language Understanding) · unknown for its base model Qwen3: training data not disclosed in enough detail

Unknown GSM8K (Grade School Math 8K) · unknown for its base model Qwen3: training data not disclosed in enough detail

Unknown MATH (Mathematics Aptitude Test of Heuristics) · unknown for its base model Qwen3: training data not disclosed in enough detail

Unknown HumanEval · unknown for its base model Qwen3: training data not disclosed in enough detail

Unknown ARC-Challenge (AI2 Reasoning Challenge, Challenge Set) · unknown for its base model Qwen3: training data not disclosed in enough detail

Unknown HellaSwag · unknown for its base model Qwen3: training data not disclosed in enough detail

Unknown TruthfulQA · unknown for its base model Qwen3: training data not disclosed in enough detail

Unknown WinoGrande · unknown for its base model Qwen3: training data not disclosed in enough detail

Multimodal LLM benchmarks

Unknown MMMU (Massive Multi-discipline Multimodal Understanding and Reasoning) · unknown for its base model Qwen3: training data not disclosed in enough detail

Unknown MMMU-Pro · unknown for its base model Qwen3: training data not disclosed in enough detail

Related data seen MathVista · in fine-tuning data: related dataset DocVQA was used

Evidence (4)
“config_name: docvqa_train”
huggingface.co · dataset card · YAML configs · retrieved 2026-10-15
“It consists of 6,141 examples, derived from 28 existing multimodal datasets involving mathematics and 3 newly created datasets”
arxiv.org · paper · Abstract · retrieved 2026-10-15
“DocVQA (2022)”
arxiv.org · paper · Table 5 (Appendix C) · retrieved 2026-10-15
“"dataset": "DocVQA",”
huggingface.co · dataset card · source.json · retrieved 2026-10-15

Seen, split unclear ChartQA · in fine-tuning data: the dataset was used; the source does not say which part

Evidence (1)
“config_name: chartqa”
huggingface.co · dataset card · YAML configs · retrieved 2026-10-15

Training data seen DocVQA · in fine-tuning data: only the training split was used, not the benchmark's test data

Evidence (1)
“config_name: docvqa_train”
huggingface.co · dataset card · YAML configs · retrieved 2026-10-15

Seen, split unclear AI2D (AI2 Diagrams) · in fine-tuning data: the dataset was used; the source does not say which part

Evidence (2)
“config_name: ai2d”
huggingface.co · dataset card · YAML configs · retrieved 2026-10-15
“while OCR (2K) and Diagram (0.2K) samples are selected from InfoVQA and AI2D, respectively.”
arxiv.org · paper · Section 5.1 RL data · retrieved 2026-10-15

Unknown CharXiv · unknown for its base model Qwen3: training data not disclosed in enough detail

Recent LLM benchmarks

Unknown GPQA Diamond · unknown for its base model Qwen3: training data not disclosed in enough detail

Unknown MMLU-Pro · unknown for its base model Qwen3: training data not disclosed in enough detail

Unknown LiveCodeBench (code generation, release_v6) · unknown for its base model Qwen3: training data not disclosed in enough detail

Unknown SWE-bench Verified · unknown for its base model Qwen3: training data not disclosed in enough detail

Unknown AIME 2024 · unknown for its base model Qwen3: training data not disclosed in enough detail

Unknown AIME 2025 · unknown for its base model Qwen3: training data not disclosed in enough detail

Unknown MATH-500 · unknown for its base model Qwen3: training data not disclosed in enough detail

Notes

Separate team/report from the 2024 LLaVA-OneVision; included as the latest LLaVA-OneVision version. The FineVision paper (used for SFT) measured 1.02% of FineVision images as near-duplicates of 66 lmms-eval test sets and states it was released 'in its original form' (not decontaminated). No decontamination statement by the LLaVA-OV-1.5 authors found. Accepts image input: “Trained on native‑resolution images, it delivers state‑of‑the‑art performance at substantially lower cost.”

Sources