deepseek-v4.1IMAGE
V4.1 Flash 1017 vs Opus 5.5、GPT-6.1 Sol：250 道难题 76.4%
250 道难题（BFCL 工具调用、Omni-MATH 7+、SuperGPQA hard）实测：Flash 76.4%、Opus 82.0%、Sol 74.8%；工具调用追平 Opus 而每次正确调用成本约 1/35，难题知识落后 Opus 11 分，硬数学题每题约 2 分钟。
Aleksey Smolenchuk
@lxe10 天前收录原推发布于 2026.10.18
Aleksey Smolenchuk @lxe原推发布于 2026.10.18
DeepSeek V4.1 Flash 1017 came out today at $0.60 per million output tokens. I ran it against Opus 5.5 and GPT-6.1 Sol on 250 hard problems (BFCL tool calls, Omni-MATH 7+, SuperGPQA hard), simple code grader on @pocketmodelai Flash 76.4% at a 128k token limit Opus 82.0% Sol 74.8% Flash ties Opus on tool calls at 1/35 the cost per correct call, and matches Sol everywhere. It trails Opus by 11 points on hard knowledge, and takes about 2 minutes per hard math problem.
x.com/lxe/status/2111576318836101135采集于 2026.10.18 16:28