List your company

Time Series Reasoning on TSUR Reasoning (test)

58.73Inductive AccuracyGEM
25.533234.151642.7751.3884Jan 29, 2026

Evaluation results

MethodLinks
GEMType=Num.+Visual2026.0158.7367.4466.35359.3
MADIType=Num.+Visual2026.0157.6867.4476.096261.98
ChatTSType=Numerical2026.0155.6651.1658.75355.5
ChatTimeType=Numerical2026.0149.1848.8453.264449.07
InstructTimeType=Numerical2026.0147.0253.49505248.25
ITFormerType=Numerical2026.0142.5444.1947.834643.48
Gemini 3 ProType=Visual2026.0136.5762.7970.656843.87
Gemini 3 ProType=Numerical2026.0134.4646.5163.046840.9
DeepSeek-V3.2Type=Numerical2026.0133.6669.7772.835640.99
Qwen3-VLType=Visual2026.0133.1151.1660.875538.75
Qwen3Type=Numerical2026.0132.3848.8468.484637.93
GPT-5.2Type=Visual2026.0132.0951.1667.395137.93
GPT-4oType=Numerical2026.0132.0760.4766.34938.22
GPT-5.2Type=Numerical2026.0130.32073.914334.23
Gemini 3 ProType=Num.+Visual2026.0130.1253.4958.76937.49
GPT-5.2Type=Num.+Visual2026.0129.9334.88754635.74
Qwen3-VLType=Num.+Visual2026.0129.751.1669.575436.76
GPT-4oType=Visual2026.0128.8662.7968.485136.03
GPT-4oType=Num.+Visual2026.0126.8155.8169.574733.93