MQA malmaud/onestop_qa Viewer • Updated Aug 8, 2024 • 1.46k • 238 • 13 tasksource/ScienceQA_text_only Viewer • Updated Jul 13, 2023 • 10.9k • 739 • 30 EleutherAI/logiqa Updated Nov 2, 2023 • 2.95k • 4 metaeval/reclor Viewer • Updated May 31, 2023 • 5.14k • 399 • 16
Small-ish SoTA (<5B), (quasi-)base nvidia/Minitron-4B-Base Text Generation • Updated Feb 14, 2025 • 4.47k • 137 h2oai/h2o-danube3-4b-base Text Generation • 4B • Updated Jul 15, 2024 • 1.56k • 22 stabilityai/stablelm-3b-4e1t Text Generation • 3B • Updated Mar 7, 2024 • 36.9k • 312 Qwen/Qwen2-1.5B Text Generation • 2B • Updated Jun 6, 2024 • 148k • • 100
SuperMC Various multiple-choice datasets, for preference learning, focused on reasoning longface/logicLM Viewer • Updated Aug 25, 2023 • 1.2k • 19 • 11 allenai/cosmos_qa Updated Jan 18, 2024 • 2.28k • 33 EleutherAI/logiqa Updated Nov 2, 2023 • 2.95k • 4 tasksource/spartqa-mchoice Viewer • Updated Jun 9, 2023 • 29.9k • 72 • 6
Interesting smol pretraining expirements UUFO-Aigis/Pico-OpenLAiNN-250M 0.3B • Updated Feb 24, 2025 • 3 • 3 crumb/distilpythia Text Generation • 95.6M • Updated Jul 20, 2023 • 228 • 4 crumb/GLORT2 Text Generation • 0.2B • Updated Aug 26, 2024 • 7 pszemraj/jamba-900M-v0.13-KIx2 Text Generation • 0.9B • Updated Dec 29, 2025 • 22 • 4
MQA malmaud/onestop_qa Viewer • Updated Aug 8, 2024 • 1.46k • 238 • 13 tasksource/ScienceQA_text_only Viewer • Updated Jul 13, 2023 • 10.9k • 739 • 30 EleutherAI/logiqa Updated Nov 2, 2023 • 2.95k • 4 metaeval/reclor Viewer • Updated May 31, 2023 • 5.14k • 399 • 16
SuperMC Various multiple-choice datasets, for preference learning, focused on reasoning longface/logicLM Viewer • Updated Aug 25, 2023 • 1.2k • 19 • 11 allenai/cosmos_qa Updated Jan 18, 2024 • 2.28k • 33 EleutherAI/logiqa Updated Nov 2, 2023 • 2.95k • 4 tasksource/spartqa-mchoice Viewer • Updated Jun 9, 2023 • 29.9k • 72 • 6
Small-ish SoTA (<5B), (quasi-)base nvidia/Minitron-4B-Base Text Generation • Updated Feb 14, 2025 • 4.47k • 137 h2oai/h2o-danube3-4b-base Text Generation • 4B • Updated Jul 15, 2024 • 1.56k • 22 stabilityai/stablelm-3b-4e1t Text Generation • 3B • Updated Mar 7, 2024 • 36.9k • 312 Qwen/Qwen2-1.5B Text Generation • 2B • Updated Jun 6, 2024 • 148k • • 100
Interesting smol pretraining expirements UUFO-Aigis/Pico-OpenLAiNN-250M 0.3B • Updated Feb 24, 2025 • 3 • 3 crumb/distilpythia Text Generation • 95.6M • Updated Jul 20, 2023 • 228 • 4 crumb/GLORT2 Text Generation • 0.2B • Updated Aug 26, 2024 • 7 pszemraj/jamba-900M-v0.13-KIx2 Text Generation • 0.9B • Updated Dec 29, 2025 • 22 • 4
