Someone has combined DeepSeek V4 Pro 0813 with a harness called J-Space, which apparently reduces errors in the extended reasoning/tool-use process.
In the benchmarks shown, DeepSeek's performance improves significantly in some cases: Terminal Bench 87.9 → 90.1, NL2Repo 61.5 → 73.4, CyberGym 83.3 → 86.8, DeepSWE 62.7 → 72.0, and Toolathlon 74.1 → 79.5.
This combination also outperforms Fable 5 and Opus 4.8 in several agentic/coding benchmarks.
Someone figured out how to unlock the true power of Deepseek-V4-Pro-0813. They fixed the thinking process errors with just a simple harness, and it completely o...