Model Releases

We analyzed DeepSeek-V4 Pro 0813 against GPT-5.6 Sol and Fable 5 on software engineering tasks using DeepSWE. DeepSeek-V4 Pro 0813 reaches 8…

We analyzed DeepSeek-V4 Pro 0813 against GPT-5.6 Sol and Fable 5 on software engineering tasks using DeepSWE. DeepSeek-V4 Pro 0813 reaches 88.5% pass@4 while costing 0.24 per task, 35x less than Sol a

DGX agentx-post
model-releasestogether-ai--x

We analyzed DeepSeek-V4 Pro 0813 against GPT-5.6 Sol and Fable 5 on software engineering tasks using DeepSWE. DeepSeek-V4 Pro 0813 reaches 88.5% pass@4 while costing 0.24 per task, 35x less than Sol and 90x less than Fable. More insights in the thread 👇 head-to-head: DeepSeek-V4 Pro 0813 vs. GPT 5.6 Sol vs. Fable 5 on software eng/DeepSWE tasks > Accuracy pass@4: 88.5% DS-V4 Pro beats both Fable and Sol > Cost: DS-V4 Pro is also 35x/90x cheaper than Sol/Fable at 0.24 per task unreal numbers tbh... full deep-dive 🧵(1/n)

Related

Source: Together AI (X) | 2026-08-15

Loading related sources…