HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/allenai/allenai/Olmo-3-1025-7B

allenai/Olmo-3-1025-7B

family olmo · 14 variants · unknown

provider
allenai
released
—
huggingface
https://huggingface.co/allenai/Olmo-3-1025-7B
best scores
MATH: 94.4BigCodeBench: 21.5HumanEval: 31.6MBPP: 36.5MMLU: 58.1MedQA: 47.3PIQA: 85.7DROP: 63.7HellaSwag: 84.0WinoGrande: 88.6BBH: 55.6MMLU-Pro: 38.8

Best scores per benchmark

benchmarkcategorybest score
MATHmath94.4
WinoGrandeknowledge88.6
PIQAknowledge85.7
HellaSwagknowledge84.0
DROPreasoning63.7
MMLUknowledge58.1
BBHreasoning55.6
MedQAdomain47.3
MMLU-Proknowledge38.8
MBPPcoding36.5
HumanEvalcoding31.6
BigCodeBenchcoding21.5

Variants (14)

variantkindquantbitsvRAMdlorgyear
Olmo-3-7B-Instruct-SFToriginalbf1616.0356,609allenai2026
Olmo-3-1025-7Boriginalbf1616.0126,941allenai2026
Olmo-3-7B-Think-SFToriginalbf1616.016,599allenai2026
Olmo-3-7B-RL-Zero-Mathoriginalbf1616.03,941allenai2026
Olmo-3-7B-RL-Zero-Mixoriginalbf1616.02,114allenai2026
Olmo-3-7B-RL-Zero-Generaloriginalbf1616.01,296allenai2026
Olmo-3-7B-RL-Zero-IForiginalbf1616.0708allenai2026
Olmo-3-7B-RL-Zero-Codeoriginalbf1616.0698allenai2026
Olmo-3.1-7B-RL-Zero-Mathoriginalbf1616.0694allenai2026
Olmo-3-1025-7B-GGUFggufgguf4.0370lmstudio-community2025
Olmo-3-1025-7B-GGUFggufgguf16.0296Mungert2025
Olmo-3.1-7B-RL-Zero-Codeoriginalbf1616.0265allenai2026
Bolmo-7Boriginalbf1616.0144allenai2026
Olmo-3-1025-7B-MLX-8bitmlxmlx49lmstudio-community2025
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.