Contamination Map Methodology

Text / LLM / Model

Olmo Hybrid 7B

Organisation
Allen Institute for AI (Ai2)
Family
OLMo
Released
2026-03-05 (Ai2 blog 'Introducing Olmo Hybrid' dated March 5, 2026 (https://allenai.org/blog/olmohybrid); arXiv 2604.03444 v1 3 Apr 2026)
Training cutoff
2024-12-01
Evidence
“Date cutoff:** Dec. 2024.”
huggingface.co · model card · Model Description · retrieved 2026-10-15
Checkpoints
allenai/Olmo-Hybrid-7B, allenai/Olmo-Hybrid-Think-SFT-7B, allenai/Olmo-Hybrid-Instruct-SFT-7B, allenai/Olmo-Hybrid-Instruct-DPO-7B
Weights
Open · apache-2.0
Links
PaperModel cardCode

Training data disclosure: Full list

Level determined for 6% of benchmark cells.

“Additionally, we use the improved data mix of Olmo 3 32B instead of the Olmo 3 7B mix.”
huggingface.co · model card · Model card intro · retrieved 2026-10-15
“The Instruct SFT and DPO data are identical to the Olmo 3 7B and 32B Instruct SFT and DPO variants.”
arxiv.org · paper · Section 5.3 · retrieved 2026-10-15

Training corpora

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

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

Not seen AIME 2025 · its test items were published from 2025-02-06, after the model's stated training-data cutoff (2024-12-01)

Evidence (3)
“Date cutoff:** Dec. 2024.”
huggingface.co · model card · Model Description · retrieved 2026-10-15
“2025 AIME I problems and solutions. The test was held on Thursday, February 6, 2025.”
web.archive.org · website · retrieved 2026-10-15
“This year the AIME I will take place on February 6, 2025, while the alternate AIME II will take place on February 12, 2025.”
maa.org · website · retrieved 2026-10-15

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

Notes

Same data pipeline as Olmo 3 (Dolma 3 + Dolci); post-trained models are preliminary (no RL stage). Decontamination is inherited from the Olmo 3 data (midtraining pool and Dolci post-training data were decontaminated in Olmo 3), but the Hybrid paper does not restate it, so no exclusions are recorded here.

Sources