GLM-5.3 matches frontier models on DeepSWE at a fraction of the cost

Together AI ran 904 DeepSWE rollouts: GLM-5.3 ties Claude Fable 5 on pass@1 (69.0% vs 69.7%) and beats GPT-5.6 Sol at pass@4 (87.6% vs 85.8%), at $3.99 per rollout vs $21.63 and $8.37 respectively. A GLM-first cascade hits 85.9% at $6.61 per task.