List your company
ResearchFormerly WizWand

Instruction Following on IFBench-I

73.96AccuracyNanoV3 Elastic-30B
11.705627.867844.0360.1922Sep 25, 2025Nov 1, 2025Dec 9, 2025Jan 15, 2026Feb 22, 2026Mar 31, 2026May 8, 2026
Updated 5mo ago

Evaluation results

MethodLinks
NanoV3 Elastic-30BModel Scale=30B, Active Parameters=3.6A, Teacher Model Status=False2026.0573.96
NanoV3-30B*Model Scale=30B, Active Parameters=3.6A, Teacher Model Status=True2026.0573.19
NanoV3 Elastic-23BModel Scale=23B, Active Parameters=2.8A, Teacher Model Status=False2026.0570.75
NanoV3 Elastic-12BModel Scale=12B, Active Parameters=2.0A, Teacher Model Status=False2026.0567.39
Qwen3-30B-A3BModel Scale=30B, Active Parameters=3.3A, Teacher Model Status=False2026.0546.57
CE-GPPOBase Model=DS-R1-Distill-Qwen-7B, Training Algorithm=CE-GPPO, Beta1 Hyperparameter=0.5, Beta2 Hyperparameter=12025.0919.8
CE-GPPOBase Model=DS-R1-Distill-Qwen-7B, Training Algorithm=CE-GPPO, Beta1 Hyperparameter=0.75, Beta2 Hyperparameter=12025.0919.7
DS-R1-Distill-Qwen-7BBase Model=DS-R1-Distill-Qwen-7B2025.0918.9
GRPOBase Model=DS-R1-Distill-Qwen-7B, Training Algorithm=GRPO2025.0918.9
DAPOBase Model=DS-R1-Distill-Qwen-7B, Training Algorithm=DAPO2025.0918.7
CE-GPPOBase Model=DS-R1-Distill-Qwen-1.5B, Training Algorithm=CE-GPPO, Beta1 Hyperparameter=0.75, Beta2 Hyperparameter=12025.0916
CE-GPPOBase Model=DS-R1-Distill-Qwen-1.5B, Training Algorithm=CE-GPPO, Beta1 Hyperparameter=0.5, Beta2 Hyperparameter=12025.0915.7
DAPOBase Model=DS-R1-Distill-Qwen-1.5B, Training Algorithm=DAPO2025.0914.8
GRPOBase Model=DS-R1-Distill-Qwen-1.5B, Training Algorithm=GRPO2025.0914.5
DS-R1-Distill-Qwen-1.5BBase Model=DS-R1-Distill-Qwen-1.5B2025.0914.1