Contamination Map Methodology

Text / LLM / Model

Gemini 4 Argon

Organisation
Google DeepMind
Family
Gemini · version 4
Released
2026-10-13 (Model card 'Published 13 October 2026' (Gemini API model page: latest update October 2026))
Training cutoff
2026-03-01
Evidence
“The knowledge cutoff for Gemini 4 is March 2026, but in some domains the model's knowledge may be less up to date.”
deepmind.google · model card · Known Limitations · retrieved 2026-10-15
Checkpoints
gemini-4-argon
Weights
Closed · proprietary
Links
Model card

Training data disclosure: Vague

Level determined for 0% of benchmark cells.

“The pre-training dataset was a large-scale, diverse collection of data encompassing a wide range of domains and modalities, which included publicly-available web-documents, text, code, images, audio (including speech and other audio types) and video.”
deepmind.google · model card · Model Data: Training Dataset · retrieved 2026-10-15
“The training dataset also includes: publicly available datasets that are readily downloadable; data obtained by crawlers; licensed data accessed via commercial agreements;”
deepmind.google · model card · Model Data: Training Dataset · retrieved 2026-10-15

Other declared training data

Benchmark cells

Classic LLM benchmarks

Unknown MMLU (Measuring Massive Multitask Language Understanding) · training data not disclosed in enough detail

Unknown GSM8K (Grade School Math 8K) · training data not disclosed in enough detail

Unknown MATH (Mathematics Aptitude Test of Heuristics) · training data not disclosed in enough detail

Unknown HumanEval · training data not disclosed in enough detail

Unknown ARC-Challenge (AI2 Reasoning Challenge, Challenge Set) · training data not disclosed in enough detail

Unknown HellaSwag · training data not disclosed in enough detail

Unknown TruthfulQA · training data not disclosed in enough detail

Unknown WinoGrande · training data not disclosed in enough detail

Multimodal LLM benchmarks

Unknown MMMU (Massive Multi-discipline Multimodal Understanding and Reasoning) · training data not disclosed in enough detail

Unknown MMMU-Pro · training data not disclosed in enough detail

Unknown MathVista · training data not disclosed in enough detail

Unknown ChartQA · training data not disclosed in enough detail

Unknown DocVQA · training data not disclosed in enough detail

Unknown AI2D (AI2 Diagrams) · training data not disclosed in enough detail

Unknown CharXiv · training data not disclosed in enough detail

Recent LLM benchmarks

Unknown GPQA Diamond · training data not disclosed in enough detail

Unknown MMLU-Pro · training data not disclosed in enough detail

Unknown LiveCodeBench (code generation, release_v6) · training data not disclosed in enough detail

Unknown SWE-bench Verified · training data not disclosed in enough detail

Unknown AIME 2024 · training data not disclosed in enough detail

Unknown AIME 2025 · training data not disclosed in enough detail

Unknown MATH-500 · training data not disclosed in enough detail

Notes

Model card: 'Gemini 4 Argon, a new frontier model, is not a modification or a fine-tune of a prior model.' No contamination or decontamination statement in the model card; evaluation methodology is on a separate DeepMind page (not fetched). Accepts image input: “Inputs Text strings (e.g., a question, a prompt, document(s) to be summarized), images, audio, and video files, with a combined input-output token context window of up to 1M.”

Sources