DeepSeek V4 Pro 0813 tops SWE-Bench in Fireworks AI evaluation
AIFireworks AI reports that DeepSeek V4 Pro 0813 scored 95.2% on SWE-Bench Verified, ahead of Kimi K3 at 92.6% and Fable 5 at 85.4%. It also says V4 Pro costs about $0.309 per solved SWE-bench task versus $0.808 for Fable 5, while scoring 48.9% on Java compared with Fable 5's 74.5%.
AIWhy it matters.
The post reports a model's benchmark results and cost per solved task against Fable 5, and it notes the Java gap plus the limits of routing as a ceiling, not a deployable policy.
Source details
Fireworks AI Blog · fireworks.aiPublished · added here
Original title: DeepSeek V4 Pro: Tops SWE-Bench & cuts cost per task by 3x vs. Fable 5