List your company

Instruction Following on MaXIFE

90.58Loose Score (MaXIFE)Gemini 3.1 Pro
60.118468.026775.93583.8433May 21, 2026

Evaluation results

MethodLinks
Gemini 3.1 ProThinking mode=true2026.0590.5887.6289.1
GPT-5.5Thinking mode=true2026.0589.9684.5887.27
Qwen3.5-397B-A17BThinking mode=true2026.0589.8886.888.34
Kimi K2.6Thinking mode=true2026.0589.1985.887.5
GLM5.1Thinking mode=true2026.0588.5985.6187.1
DeepSeek-V4-ProThinking mode=true2026.0588.5384.1486.34
GPT-5.5Thinking mode=false2026.0587.0481.0484.04
Kimi K2.6Thinking mode=false2026.0586.480.4983.45
GLM5.1Thinking mode=false2026.0586.480.4983.45
Qwen3.5-397B-A17BThinking mode=false2026.0586.2680.4683.36
DeepSeek-V4-ProThinking mode=false2026.0584.9878.7781.88
Gemma4-26B-A4BThinking mode=false2026.0584.8779.2582.06
Gemma4-E4BThinking mode=false2026.0581.5874.8378.21
Qwen3.6-35B-A3BThinking mode=false2026.0580.7273.3977.06
Hy-MT2-30B-A3BThinking mode=false2026.0580.4674.3177.39
Gemma4-E2BThinking mode=false2026.0577.3268.7973.06
Hy-MT2-7BThinking mode=false2026.0576.7768.7372.75
Hy-MT2-1.8BThinking mode=false2026.0561.2951.0556.17