List your company

Data Prediction on DSPredict Hard (Private test)

85.7Valid ScoreGPT-5.1
1.56423.40745.2567.093Jan 22, 2026

Evaluation results

MethodLinks
GPT-5.1reasoning=high2026.0185.74.814.3
Claude Sonnet 42026.0185.72.44.8
GPT-5.1reasoning=medium2026.01814.87.1
Deepseek v3.12026.0176.22.47.1
Claude Sonnet 4.52026.0171.404.8
GPT-5.1reasoning=none2026.01692.410.3
Kimi K2 Instruct2026.016900
Qwen3-Coderparameters=480B2026.0166.72.45.9
Qwen3 Instructparameters=235B2026.0164.32.42.4
GPT-5reasoning=medium2026.0152.402.4
Qwen3 Instructparameters=4B2026.0140.500
Qwen2.5 Instructparameters=7B2026.014.800