List your company

Instruction Following on WildBench (test)

58.6Info SeekGPT-4o
-31.152-7.85115.4538.751Jan 7, 2026

Evaluation results

MethodLinks
GPT-4oModel Type=Proprietary2026.0158.659.160.560.257.359.3
GPT-4-turboModel Type=Proprietary2026.0157.258.755.156.25155.2
DeepSeek-V2-ChatModel Type=Chat2026.0152.756.45554.851.454
OriginalBackbone=Qwen-2.5-7B, Setting=Instruct2026.0147.244.544.748.944.445.4
STEPSBackbone=Llama-3-8B, Setting=Instruct2026.0146.125.237.942.918.936.3
STEPSBackbone=Qwen-2.5-7B, Setting=Instruct2026.014445.149.148.345.545.7
Instruct-SkillMixBackbone=Qwen-2.5-7B, Setting=Instruct2026.0141.936.641.740.83739.6
STEPSBackbone=Mistral-7B-v0.3, Setting=Instruct2026.0139.616.530.837.81029
OriginalBackbone=Mistral-7B-v0.3, Setting=Instruct2026.0139.520.729.333.78.528.6
STEPSBackbone=Qwen-2.5-7B, Setting=Base2026.0139.334.531.139.53435.1
Instruct-SkillMixBackbone=Llama-3-8B, Setting=Instruct2026.0139.120.632.537.715.730.8
OriginalBackbone=Llama-3-8B, Setting=Instruct2026.0137.9432635.822.434.2
Instruct-SkillMixBackbone=Qwen-2.5-7B, Setting=Base2026.0135.333.827.936.131.732.8
STEPSBackbone=Llama-3-8B, Setting=Base2026.0130.67.726.830.612.323
Instruct-SkillMixBackbone=Llama-3-8B, Setting=Base2026.0122.413.823.926.49.719.7
STEPSBackbone=Mistral-7B-v0.3, Setting=Base2026.0121.9-6.717.124.3-5.211.3
OriginalBackbone=Qwen-2.5-7B, Setting=Base2026.0121.56.55.312.55.510.7
Instruct-SkillMixBackbone=Mistral-7B-v0.3, Setting=Instruct2026.0118.62.312.111.8-3.110.3
Alpaca52kBackbone=Llama-3-8B, Setting=Instruct2026.0115.9-10.44.111.3-9.15
Instruct-SkillMixBackbone=Mistral-7B-v0.3, Setting=Base2026.019.3-6.59.314-7.85.2
Alpaca52kBackbone=Llama-3-8B, Setting=Base2026.010.5-18.6-6.50.4-16.6-6.1
Alpaca52kBackbone=Qwen-2.5-7B, Setting=Base2026.01-6.3-5.4-23.3-7.7-3.8
Alpaca52kBackbone=Qwen-2.5-7B, Setting=Instruct2026.01-13.4-14.3-9.1-6.5-14.1-11.4
Alpaca52kBackbone=Mistral-7B-v0.3, Setting=Instruct2026.01-13.6-26.6-13.2-8.2-12.5-14.8
Alpaca52kBackbone=Mistral-7B-v0.3, Setting=Base2026.01-14.2-24.8-13.7-5.1-20-14
OriginalBackbone=Mistral-7B-v0.3, Setting=Base2026.01-26.1-28.1-21.2-9.3-29.8-22.7
OriginalBackbone=Llama-3-8B, Setting=Base2026.01-27.7-30.4-23.8-17.1-29.8-25.7