Chubby♨️@kimmonismusDeepSeek 4 GA 基准测试已流传，性能提升扎实，但对比对象是 Opus 4.8 而非 Opus 5。测试结果稳定，与开源 SOTA 模型 Kimi k3 和 GLM-5.2 持平，接近 5.6 Sol 和 Fable 5 的表现。DeepSeek v4 Pro GA 与 Grok 4.6 API 同步推出。
Here we go: DeepSeek 4 GA Benchmarks are circulating already.
A very solid upgrade, but it's a bit of a shame they're comparing it to Opus 4.8 instead of Opus 5.
The results are consistently good, putting it on par with open-source SOTA (Kimi k3 and GLM-5.2) and approaching the performance of 5.6 Sol and Fable 5.
来源：Chubby♨️ · x.com
DeepSeek 4 GA 基准测试已流传，性能提升扎实，但对比对象是 Opus 4.8 而非 Opus 5。测试结果稳定，与开源 SOTA 模型 Kimi k3 和 GLM-5.2 持平，接近 5.6 Sol 和 Fable 5 的表现。DeepSeek v4 Pro GA 与 Grok 4.6 API 同步推出。
Here we go: DeepSeek 4 GA Benchmarks are circulating already.
A very solid upgrade, but it's a bit of a shame they're comparing it to Opus 4.8 instead of Opus 5.
The results are consistently good, putting it on par with open-source SOTA (Kimi k3 and GLM-5.2) and approaching the performance of 5.6 Sol and Fable 5.
来源：Chubby♨️· x.com