Share your thoughts, 1 month free Claude Pro on usSee more

Remote Code Execution Exploit Generation on RCE (test)

16.96Total Score

GPT-o3

Updated 1mo ago

Evaluation Results

Method	Links
GPT-o3 2026.06		16.96	79	15	3.56	1.06	2.28	2.79	3.31	2.99
GPT-5.2 2026.06		16.12	68	41	3.35	1.13	2.06	2.77	3.04	2.6
Kimi-K2.5 2026.06		14.54	50	12	3.39	1	2.02	2.36	2.57	2.59
Claude Opus 4.6 2026.06		14.37	68	14	2.85	1.03	1.96	2.37	2.49	2.84
DeepSeek-R1 2026.06		13.04	53	7	3.22	0.89	1.8	2.22	2.27	2
Claude Sonnet 4.5 2026.06		12.66	58	6	2.91	0.89	1.74	2.15	2.1	2.21
Qwen3-235B 2026.06		12.21	33	6	3.08	0.82	1.67	2.36	1.97	1.91
Qwen3-Coder-480B 2026.06		11.08	41	3	2.92	0.73	1.52	1.84	1.96	1.64
Claude Sonnet 3.7 2026.06		11.03	51	1	2.48	0.76	1.58	1.78	2.01	1.92
Qwen3-30B 2026.06		10.44	31	1	2.93	0.71	1.5	1.93	1.58	1.4
DeepSeek-V3.2 2026.06		10.32	52	11	2.48	0.74	1.4	1.84	1.73	1.51
Llama4-Maverick-400B 2026.06		7.36	20	0	2.09	0.42	1.04	1.21	1.11	1.26
GPT-4o 2026.06		7.09	28	1	1.94	0.41	1.01	1.19	1.2	0.97
Qwen3-8B 2026.06		6.58	20	0	1.93	0.37	0.9	1.31	1.04	0.77
Qwen3-14B 2026.06		6.21	15	0	1.81	0.34	0.87	1.26	0.9	0.84
Llama4-Scout-109B 2026.06		6.06	21	0	1.83	0.33	0.79	1.15	0.86	0.88
GPT-5 2026.06		4.1	9	6	0.43	0.15	0.26	2.24	0.42	0.35