DeepSeek Harness 让 V4.1 Flash 跑分平均高 2–3 分，但成本高 80%
同一基准下 DeepSeek harness 最高档均分 42.7，高于 Claude Code harness 的 39.1，也超过 Opus 5.5 的 41.7，仅次于 GPT-6 Astra 的 45。
Turns out DeepSeek harness improves the score of DeepSeek V4.1 Flash by 2-3 points on average. It also costs 80% more due to subagents and more output tokens. New results: DeepSeek V4.1 Flash 1017 + Claude Code harness: - max, mean of 7: 39.1 - high, mean of 5: 36.4 - low, mean of 5: 34.4 DeepSeek V4.1 Flash 1017 + DeepSeek harness: - max, mean of 7: 42.7 - high, mean of 5: 39.2 - low, mean of 5: 34.8 For comparison: GPT-6 Astra, max: 45 Opus 5.5, max: 41.7 Muse Wonder Full 1.0, max: 42 It's a crazy model, and the only one catched cheating. All the results are available on the benchmark website.
这条是引用着另一条写的：「多模型跑分对比：Gemini 4 Argon 40.7 居第三」