Purpose To examine the prognosis and prognostic factors for patients with chronic low back pain presenting to a private, community-based, group exercise program. Methods A total of 118 consecutive patients with chronic LBP were recruited. Baseline assessments included sociodemographic characteristics, back pain history and clinical examination findings. Primary outcome measures were pain intensity and disability at 3, 6 and 12 months. Potential prognostic factors to predict pain intensity and disability at 12 months were assessed using a multivariate regression model. Results 112 (95 %) participants were followed up at 12 months. The majority of participants were female (73 %), had high educational levels (82 %) and resided in suburbs with a high socio-economic status (99 %). Pain intensity improved markedly during the first 6 months (35 %) with further minimal reductions up to 12 months (39 %). Interestingly, disability improved to a greater degree than pain (48 % improvement at 6 months) and continued to improve throughout the 12 months (60 %). Baseline pain intensity accounted for 10 % of the variance in the 1 year pain outcomes. Duration of current episode, baseline disability and educational level accounted for 15 % of the variation in disability at 12 months. Conclusions During a period of 12 months, patients with chronic LBP presenting to a private, community-based, group exercise program improved markedly, with greater improvements in disability than pain. The predictors investigated accounted for only 10 and 15 % of pain and disability outcomes, respectively.