快捷总览
【简评】这一场比赛综合来看,是近期以来最难的一场。前期题设置以构造/思维为主,极大的破坏了 AI 的优势;但是在 C 题这样的传统数学题上,AI 依旧轻松扳回一城。
本场 AI 的排名在总排行榜的 80~140 之间(答出四题)。
AI评估与代码查看
【备注】本周来自供应商 Cursor 的 Grok-4 模型接口非常的不稳定,很遗憾没能在有限的验题时间内检验更多的题目 :(
[00:13:00] [B] Grok-4 (from Cursor) Accept! Click for code. CodeForces ≈ 2200 图论、BFS、组件压缩建模、DAG上最大路径DP、视野受限可达性判断 [00:20:16] [B] o3-Pro Wrong Answer. 3/46. [00:32:07] [B] o3-Pro Accept! Click for code. CodeForces ≈ 2100 单调列DP、列内连通段闭包、反向BFS、有限视野可达性模拟 [00:07:27] [C] o3-Pro Wrong Answer. 22/34. [00:33:47] [C] o3-Pro Wrong Answer. 32/34. [00:43:01] [C] o3-Pro Wrong Answer. 32/34. [00:50:50] [C] o3-Pro Wrong Answer. 32/34. [00:55:56] [C] o3-Pro Wrong Answer. 32/34. [00:56:15] [C] o3-Pro Accept! Click for code. CodeForces ≈ 2500 组合数学(Narayana 数、模组合计数)、大数落阶乘、数论取模 [01:07:12] [D] o3-Pro Wrong Answer. 24/32. [01:09:36] [D] o3-Pro Wrong Answer. 24/32. [00:06:44] [E] o3-Pro Wrong Answer. 4/36. [00:14:11] [E] o3-Pro Wrong Answer. 7/36. [00:18:01] [E] o3-Pro Wrong Answer. 15/36. [00:21:59] [E] Grok-4 (from Cursor) Memory Limit Exceed. 0/36. [00:23:59] [E] Grok-4 (from Cursor) Wrong Answer. 2/36. [00:27:50] [E] o3-Pro Accept! Click for code. CodeForces ≈ 2400 重链剖分、线段树区间函数合成、有限状态自动机(25 状态 bitmask)、树上路径查询 [00:02:32] [F] Grok-4 (from Cursor) Accept! Click for code. CodeForces ≈ 1700 贪心算法、排序、有效价值计算 [00:01:00] [F] o3-Pro Accept! Click for code. CodeForces ≈ 1600 贪心、数值转换、排序 [00:13:05] [G] o3-Pro Give up. [00:25:29] [G] Grok-4 (from Cursor) Wrong Answer. 2/31. [01:07:19] [G] Grok-4 (from Cursor) Wrong Answer. 4/31. [00:04:10] [H] o3-Pro Time limit exceeded. 11/54. [00:17:25] [H] o3-Pro Time limit exceeded. 13/54. [00:25:02] [H] o3-Pro Wrong Answer. 7/54. [00:34:40] [H] o3-Pro Time limit exceeded. 16/54. [00:35:19] [H] o3-Pro Runtime Error. 18/54. [00:35:51] [H] o3-Pro Wrong Answer. 21/54. [00:36:40] [H] o3-Pro Time limit exceeded. 20/54. [00:37:55] [H] o3-Pro Wrong Answer. 15/54. [00:04:53] [I] o3-Pro Wrong Answer. 13/44. [00:14:04] [I] o3-Pro Wrong Answer. 13/44. [00:22:03] [I] o3-Pro Wrong Answer. 13/44. [00:21:32] [J] o3-Pro Wrong Answer. 16/26. [00:31:39] [J] o3-Pro Wrong Answer. 16/26. [00:35:11] [J] o3-Pro Wrong Answer. 16/26. [00:11:01] [K] o3-Pro Runtime Error. 0/26. [00:24:43] [K] o3-Pro Runtime Error. 0/26. [00:33:16] [K] o3-Pro Wrong Answer. 0/26. [00:13:57] [K] o3-Pro Time limit exceeded. 10/20. [00:15:00] [K] Grok-4 (from Cursor) Time limit exceeded. 10/20. [00:39:00] [K] Grok-4 (from Cursor) Wrong Answer. 6/20. [00:43:45] [K] Grok-4 (from Cursor) Time limit exceeded. 10/20. [00:48:24] [K] Grok-4 (from Cursor) Time limit exceeded. 10/20. [00:09:18] [M] o3-Pro Give up.
全部评论
(0) 回帖