List your company

Multitask Language Understanding on MMLU (pass@1)

71.9pass@1Tulu 3-SFT
37.351246.320655.2964.2594Oct 18, 2024Jan 6, 2025Mar 27, 2025Jun 16, 2025Sep 4, 2025Nov 23, 2025Feb 12, 2026

Evaluation results

MethodLinks
Tulu 3-SFTBase model=Qwen-2.5-7B2024.1071.9
MATRIX-Gen-SFTBase model=Qwen-2.5-7B2024.1071.9
OpenHermesBase model=Qwen-2.5-7B2024.1069.6
WildChatBase model=Qwen-2.5-7B2024.1069.3
Tulu v2 MixBase model=Qwen-2.5-7B2024.1069
Evol-InstructBase model=Qwen-2.5-7B2024.1068.3
ShareGPTBase model=Qwen-2.5-7B2024.1067.8
Magpie-SFTBase model=Qwen-2.5-7B2024.1067
Magpie-SFTBase model=Meta-Llama-3-8B2024.1061.2
MATRIX-Gen-SFTBase model=Meta-Llama-3-8B2024.1059.9
ShareGPTBase model=Meta-Llama-3-8B2024.1058.4
Tulu v2 MixBase model=Meta-Llama-3-8B2024.1058.4
Tulu 3-SFTBase model=Meta-Llama-3-8B2024.1057.8
Dare Ties MergingModel=Fused2026.0255.64
Task ArithmeticModel=Fused2026.0255.58
w/o MergingModel=Meta-Llama-3-8B-Instruct (base0)2026.0255.11
OpenHermesBase model=Meta-Llama-3-8B2024.1052.8
Ties MergingModel=Fused2026.0252.04
Evol-InstructBase model=Meta-Llama-3-8B2024.1048
SCF-RKLModel=Fused2026.0246.17
Dare Task ArithmeticModel=Fused2026.0245.54
WildChatBase model=Meta-Llama-3-8B2024.1043.1
SCEModel=Fused2026.0242.85
w/o MergingModel=MAmmoTH2-8B-Plus (base1)2026.0238.68