Model Releases
We analyzed DeepSeek V4 Flash and GPT-5.6 Luna on DeepSWE. A DeepSeek-first cascade with test-suite verification solved MORE tasks than Luna…
Researchers from TogetherAI analyzed DeepSeek V4 Flash and GPT‑5.6 Luna on the DeepSWE benchmark. The study found that employing a DeepSeek‑first cascade with test‑suite verification solved more tasks
Researchers from TogetherAI analyzed DeepSeek V4 Flash and GPT‑5.6 Luna on the DeepSWE benchmark. The study found that employing a DeepSeek‑first cascade with test‑suite verification solved more tasks than Luna alone, achieving a 37 % lower cost per task. The results were presented on August 8, 2026.
Related
- We analyzed DeepSeek-V4 Flash-0731 vs. GPT-5.6 Luna on software engineering tasks using DeepSWE. DeepSeek-V4 Flash-0731 delivers 80% of Luna…
- DeepSeek-V4 Flash 0731 vs GPT-5.6 Luna on DeepSWE: Cost and Coding
Source: Together AI (X) | 2026-08-08