AI model leaderboards

See top models, labs, apps, and providers on AI Gateway with token, request, and cost trends.

DeepsecBench measures how well different AI models find security vulnerabilities in application code, based on the deepsec cyber harness(opens in new tab). The report combines recall and precision into a single benchmark score.

Score vs. cost

Pareto Frontier

Score vs. total time

Pareto Frontier

Results


1	GPT-6 Sol xhighopenai/gpt-6-sol	40.91	35.8%	96.0%	4	$12.76	1h 09m 09s	1,716.8	Codex
2	GPT-6 Astra xhighopenai/gpt-6-astra	37.79	32.8%	97.9%	2	$63.70	49m 47s	1,683.9	Codex
3	GPT-5.6 Sol xhighopenai/gpt-5.6-sol	35.44	30.6%	96.3%	3	$55.98	3h 39m 02s	2,274.9	Codex
4	Claude Opus 5 maxanthropic/claude-opus-5	32.44	28.0%	88.0%	10	$127.93	2h 34m 19s	4,453.7	Claude Code
5	GPT-6 Astra mediumopenai/gpt-6-astra	29.33	25.0%	95.5%	3	$35.20	21m 49s	973.0	Codex
6	GPT-6 Sol mediumopenai/gpt-6-sol	29.31	25.0%	94.2%	4	$12.05	28m 08s	932.1	Codex
7	Claude Opus 5 mediumanthropic/claude-opus-5	28.25	24.6%	70.5%	26	$31.96	47m 01s	999.7	Claude Code
8	GPT-5.6 Luna xhighopenai/gpt-5.6-luna	26.68	22.8%	81.2%	13	$24.59	3h 01m 40s	3,343.4	Codex
9	Claude Opus 5.5 maxanthropic/claude-opus-5.5	26.68	22.8%	81.0%	15	$40.31	3h 51m 08s	1,175.1	Claude Code
10	GPT-5.6 Sol mediumopenai/gpt-5.6-sol	25.00	21.1%	94.3%	3	$17.95	30m 52s	703.0	Codex
11	GLM-5.3 highzai/glm-5.3	21.91	18.5%	80.7%	11	$16.22	2h 05m 37s	1,232.1	Pi
12	GPT-5.5 xhighopenai/gpt-5.5	21.11	17.7%	95.5%	2	$43.42	2h 22m 57s	2,158.8	Codex
13	GPT-6 Luna xhighopenai/gpt-6-luna	21.05	17.7%	89.6%	5	$0.51	1h 00m 36s	1,423.5	Codex
14	GLM-5.3 maxzai/glm-5.3	20.39	17.2%	75.9%	13	$14.60	1h 29m 34s	1,241.8	Pi
15	GPT-5.6 Terra xhighopenai/gpt-5.6-terra	19.14	15.9%	95.3%	2	$27.81	1h 45m 32s	2,108.7	Codex
16	Kimi K3 xhighmoonshotai/kimi-k3	17.49	14.7%	77.1%	11	$12.38	1h 59m 39s	731.9	Pi
17	Claude Sonnet 5 maxanthropic/claude-sonnet-5	16.99	14.2%	76.1%	11	$45.17	3h 08m 20s	4,601.8	Claude Code
18	Deepseek V4 Flash xhighdeepseek/deepseek-v4-flash	16.47	13.8%	74.0%	13	$5.94	1h 18m 09s	1,481.0	Pi
19	Qwen3.8 Max xhighalibaba/qwen3.8-max	16.47	13.8%	73.9%	12	$6.33	1h 52m 20s	342.6	Pi
20	Grok 4.5 mediumxai/grok-4.5	16.47	13.8%	73.3%	12	$11.04	1h 37m 33s	909.6	Pi
21	Grok 4.6 xhighxai/grok-4.6	16.16	13.4%	100.0%	0	$22.29	4h 02m 36s	3,456.4	Pi
22	Qwen3.8 Max mediumalibaba/qwen3.8-max	15.53	12.9%	78.9%	8	$6.22	2h 03m 33s	383.4	Pi
23	Grok 4.5 xhighxai/grok-4.5	15.52	12.9%	77.8%	10	$5.60	1h 24m 17s	1,010.5	Pi
24	Deepseek V4 Flash mediumdeepseek/deepseek-v4-flash	15.42	12.9%	66.7%	16	$5.06	1h 21m 16s	1,422.5	Pi
25	GPT-6 Luna mediumopenai/gpt-6-luna	13.58	11.2%	89.7%	3	$1.75	24m 56s	873.5	Codex
26	GLM-5.3 Flash highzai/glm-5.3-flash	12.98	10.8%	64.3%	15	$0.35	21m 21s	1,264.6	Pi
27	GPT-5.5 mediumopenai/gpt-5.5	12.58	10.3%	92.3%	2	$14.94	24m 05s	751.4	Codex
28	GPT-5.6 Terra mediumopenai/gpt-5.6-terra	12.07	9.9%	92.0%	2	$5.15	13m 15s	617.7	Codex
29	GPT-5.6 Luna mediumopenai/gpt-5.6-luna	12.03	9.9%	82.8%	5	$5.23	11m 59s	572.0	Codex
30	Gemini 3.6 Flash mediumgoogle/gemini-3.6-flash	11.51	9.5%	80.0%	6	$10.74	26m 21s	2,730.7	Pi
31	Kimi K3 mediummoonshotai/kimi-k3	11.43	9.5%	64.1%	14	$10.84	1h 29m 16s	676.6	Pi
32	GLM-5.3 Flash maxzai/glm-5.3-flash	10.96	9.1%	62.5%	15	$1.83	41m 04s	1,598.4	Pi
33	Grok 4.7 xhighspacexai/grok-4.7	10.93	9.1%	64.7%	12	$13.28	42m 23s	1,703.4	Pi
34	GLM-5.2 mediumzai/glm-5.2	10.42	8.6%	62.5%	12	$11.09	1h 03m 38s	1,498.9	Pi
35	Claude Opus 5.5 mediumanthropic/claude-opus-5.5	9.99	8.2%	82.6%	4	$7.32	07m 01s	38.0	Claude Code
36	GLM-5.2 xhighzai/glm-5.2	9.86	8.2%	53.8%	18	$51.84	2h 30m 44s	4,727.6	Pi
37	Gemini 3.6 Flash xhighgoogle/gemini-3.6-flash	8.95	7.3%	77.3%	5	$5.33	22m 18s	1,822.4	Pi
38	Grok 4.7 mediumspacexai/grok-4.7	7.84	6.5%	53.3%	14	$3.97	21m 28s	904.5	Pi
39	Claude Opus 4.8 maxanthropic/claude-opus-4.8	6.89	5.6%	81.3%	3	$7.56	19m 29s	80.8	Claude Code
40	Claude Opus 4.8 mediumanthropic/claude-opus-4.8	6.85	5.6%	61.9%	8	$10.81	18m 16s	78.1	Claude Code
41	Inkling xhighthinkingmachines/inkling	6.30	5.2%	48.0%	13	$1.93	11m 34s	300.9	Pi
42	Claude Sonnet 5 mediumanthropic/claude-sonnet-5	5.81	4.7%	61.1%	7	$6.66	15m 47s	442.2	Claude Code
43	Inkling mediumthinkingmachines/inkling	5.24	4.3%	37.0%	17	$2.18	10m 31s	509.0	Pi
44	Claude Haiku 4.5 defaultanthropic/claude-haiku-4.5	4.71	3.9%	33.3%	18	$5.91	29m 40s	912.4	Claude Code
45	Gemini 3.5 Flash Lite mediumgoogle/gemini-3.5-flash-lite	2.13	1.7%	44.4%	5	$0.58	01m 46s	459.9	Pi
46	Gemini 3.5 Flash Lite xhighgoogle/gemini-3.5-flash-lite	1.07	0.9%	28.6%	5	$0.18	01m 07s	406.5	Pi