List your company

Instruction Following on IFEval v1 (test)

79.85AccuracyEntropy
21.131636.375851.6266.8642Jul 15, 2024Nov 5, 2024Feb 26, 2025Jun 20, 2025Oct 11, 2025Feb 1, 2026May 26, 2026

Evaluation results

MethodLinks
EntropySetting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0579.85
Pure OPDSetting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0579.11
TA-OPDSetting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0578.93
TA-OPD+Ent.Setting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0577.54
TIPSetting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0576.71
TIPSetting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0576.62
TA-OPDSetting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0575.13
EntropySetting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0573.94
BaseSetting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0573.57
BaseSetting=Qwen3-14B -> Qwen3-4B, Supervised-token budget=10%2026.0573.57
TA-OPD+Ent.Setting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0573.38
Llama-3-8BInstruction-tuned=true, evaluation_protocol=strict-prompt2024.0772.1
Pure OPDSetting=Qwen3-8B (GRPO) -> Qwen3-4B, Supervised-token budget=10%2026.0570.33
GLM-4-9BInstruction-tuned=true, evaluation_protocol=strict-prompt2024.0769
TA-OPDSetting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0564.05
Pure OPDSetting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0562.85
TA-OPD+Ent.Setting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0561.73
TIPSetting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0560.91
EntropySetting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0560.63
BaseSetting=Qwen3-4B -> Qwen3-1.7B, Supervised-token budget=10%2026.0559.52
Qwen2-7BInstruction-tuned=true, evaluation_protocol=strict-prompt2024.0754.7
Qwen1.5-7BInstruction-tuned=true, evaluation_protocol=strict-prompt2024.0738.3
BaseSetting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.0526.16
TIPSetting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.0526.16
TA-OPDSetting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.0525.42
EntropySetting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.0524.68
Pure OPDSetting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.0523.48
TA-OPD+Ent.Setting=DeepSeek-R1-Distill-Qwen-14B -> Qwen2.5-3B, Supervised-token budget=10%2026.0523.39