List your company

Instruction Following on IFEval (Avg@k, Pass@k)

64.23Avg@kBase
30.398839.181947.96556.7481May 8, 2026

Evaluation results

MethodLinks
BaseBackbone=Qwen2.5-7B-Instruct2026.0564.2376.71
DFTBackbone=Qwen2.5-7B-Instruct2026.0561.1873.01
DFTBase Model=Qwen2.5-7B-Instruct, RL Stage=DAPO, k=42026.0561.1873.01
RPSFTBackbone=Qwen2.5-7B-Instruct2026.0558.3273.38
RPSFTBase Model=Qwen2.5-7B-Instruct, RL Stage=DAPO, k=42026.0558.3273.38
BaseBackbone=Qwen2.5-3B-Instruct2026.0558.0970.61
IWBackbone=Qwen2.5-7B-Instruct2026.0555.9169.5
IWBase Model=Qwen2.5-7B-Instruct, RL Stage=DAPO, k=42026.0555.9169.5
SFTBackbone=Qwen2.5-7B-Instruct2026.0554.4869.5
SFTBase Model=Qwen2.5-7B-Instruct, RL Stage=DAPO, k=42026.0554.4869.5
DFTBackbone=Qwen2.5-3B-Instruct2026.0552.5965.62
DFTBase Model=Qwen2.5-3B-Instruct, RL Stage=DAPO, k=42026.0552.5965.62
RPSFTBackbone=Qwen2.5-3B-Instruct2026.0549.7265.25
RPSFTBase Model=Qwen2.5-3B-Instruct, RL Stage=DAPO, k=42026.0549.7265.25
SFTBackbone=Qwen2.5-3B-Instruct2026.0547.9763.03
SFTBase Model=Qwen2.5-3B-Instruct, RL Stage=DAPO, k=42026.0547.9763.03
IWBackbone=Qwen2.5-3B-Instruct2026.0547.9262.85
IWBase Model=Qwen2.5-3B-Instruct, RL Stage=DAPO, k=42026.0547.9262.85
SFTBackbone=Llama-3.1-8B-Instruct2026.0532.5835.49
SFTBase Model=Llama-3.1-8B-Instruct, RL Stage=DAPO, k=42026.0532.5835.49
BaseBackbone=Llama-3.1-8B-Instruct2026.0532.335.86
RPSFTBackbone=Llama-3.1-8B-Instruct2026.0531.9335.67
RPSFTBase Model=Llama-3.1-8B-Instruct, RL Stage=DAPO, k=42026.0531.9335.67
DFTBackbone=Llama-3.1-8B-Instruct2026.0531.8434.57
DFTBase Model=Llama-3.1-8B-Instruct, RL Stage=DAPO, k=42026.0531.8434.57
IWBackbone=Llama-3.1-8B-Instruct2026.0531.735.3
IWBase Model=Llama-3.1-8B-Instruct, RL Stage=DAPO, k=42026.0531.735.3