List your company

Instruction Following on WritingBench

81Average ScoreClaude-Opus-4.7
30.24843.42456.669.776May 8, 2026

Evaluation results

MethodLinks
Claude-Opus-4.7Stage=-2026.0581
QwQ-32BStage=-2026.0579.1
R1-0528-Qwen3-8BStage=Iter32026.0576.5
R1-0528-Qwen3-8BStage=Iter12026.0576.3
R1-0528-Qwen3-8BStage=BASE2026.0576.1
R1-0528-Qwen3-8BStage=Iter22026.0576.1
GPT-4oStage=-2026.0575.5
Qwen2.5-7B-InstructStage=Iter32026.0563.8
Qwen2.5-7B-InstructStage=Iter22026.0563.3
Qwen2.5-7B-InstructStage=Iter12026.0563.1
Distill-Qwen-14BStage=Iter32026.0562.1
RAIF-7BStage=-2026.0561.7
Distill-Qwen-14BStage=Iter22026.0561.4
Distill-Qwen-14BStage=BASE2026.0561
Distill-Qwen-14BStage=Iter12026.0560.8
Self-Supervised-7BStage=-2026.0558.5
Qwen2.5-7B-InstructStage=BASE2026.0557.2
VERIF-8BStage=-2026.0550.8
Llama-3.1-8B-InstructStage=BASE2026.0547.5
Llama-3.1-8B-InstructStage=Iter32026.0547.4
Llama-3.1-8B-InstructStage=Iter12026.0547.2
Llama-3.1-8B-InstructStage=Iter22026.0547.1
SPAR-8B-DPOStage=-2026.0547
Qwen2.5-1.5B-InstructStage=Iter12026.0545.6
Qwen2.5-1.5B-InstructStage=Iter32026.0545.6
Crab-7B-DPOStage=-2026.0545.4
Qwen2.5-1.5B-InstructStage=Iter22026.0545.4
Qwen2.5-1.5B-InstructStage=BASE2026.0544.8
Conifer-7B-DPOStage=-2026.0532.2