ModelsAug 15, 2026 · 12:351 source

DeepSeek V4 Pro Hits 88.5% on Coding Benchmarks, Beating Fable 5 at 90x Lower Cost

From huggingnews.com

AI;DR

Together AI tested the DeepSeek-V4 Pro 0813 model against GPT-5.6 Sol and Fable 5 using the DeepSWE benchmark, where it achieved an 88.5% pass@4 rate. At a cost of $0.24 per task, the model is 35 times cheaper than Sol and 90 times cheaper than Fable. DeepSeek transitioned the V4 Pro model to a production release on Aug. 13 and will implement new dynamic pricing for the V4 lineup on Aug. 16.

Read the sourceSign in to suggest

Sources

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today