List your company

Knowledge & Instruction Following on MMLU

88.21ScoreQwen3.5-9B (released)
61.887668.721375.55582.3887Jun 1, 2026

Evaluation results

MethodLinks
Qwen3.5-9B (released)Model Size=9B, Training Protocol=Released, Decoding Strategy=Native AR decoding2026.0688.21
Qwen3.5-9BParams=9B, Sampling mode=AR2026.0688.21
LLaDA-2.0-flashParams=100B-A5B, Sampling mode=Diffusion2026.0687.69
Qwen3.5-9B + AR-SFTModel Size=9B, Training Protocol=AR-SFT, Decoding Strategy=Native AR decoding2026.0686.07
Qwen3.5-4B (released)Model Size=4B, Training Protocol=Released, Decoding Strategy=Native AR decoding2026.0685.22
Qwen3.5Params=4B, Sampling mode=AR2026.0685.22
FLARE-9BModel Size=9B, Training Protocol=FLARE, Decoding Strategy=AR-Trust sampling2026.0684.8
FLARE-9BParams=9B, Sampling mode=AR-Trust2026.0684.8
SDAR 30B-A3BParams=30B-A3B, Sampling mode=Diffusion2026.0682.8
Qwen3.5-4B + AR-SFTModel Size=4B, Training Protocol=AR-SFT, Decoding Strategy=Native AR decoding2026.0680.75
FLARE-9BParams=9B, Sampling mode=Diffusion-Trust2026.0680.75
LLaDA-2.0-miniParams=16B-A1B, Sampling mode=Diffusion2026.0680.53
FLAREParams=4B, Sampling mode=Diffusion-Trust2026.0679.54
FLARE-4BModel Size=4B, Training Protocol=FLARE, Decoding Strategy=AR-Trust sampling2026.0678.73
FLAREParams=4B, Sampling mode=AR-Trust2026.0678.73
SDARParams=8B, Sampling mode=Diffusion2026.0678.6
SDARParams=4B, Sampling mode=Diffusion2026.0674.9
Qwen3.5-2B (released)Model Size=2B, Training Protocol=Released, Decoding Strategy=Native AR decoding2026.0673.59
Qwen3.5Params=2B, Sampling mode=AR2026.0673.59
Qwen3.5-2B + AR-SFTModel Size=2B, Training Protocol=AR-SFT, Decoding Strategy=Native AR decoding2026.0668.63
FLARE-2BModel Size=2B, Training Protocol=FLARE, Decoding Strategy=AR-Trust sampling2026.0667.6
FLAREParams=2B, Sampling mode=AR-Trust2026.0667.6
FLAREParams=2B, Sampling mode=Diffusion-Trust2026.0664.14
SDARParams=1.7B, Sampling mode=Diffusion2026.0662.9