Skip to content

AI model leaderboards

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

DeepsecBench

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.

OpenAI
Anthropic
Moonshot AI
xAI
Google
Z.ai
Thinking Machines

Score vs Cost

010203040$0$50$100$150Cost (USD)Score

Score vs Total Time

0102030400h1h2h3h4hTotal timeScore

Ranked results

1
GPT-5.6 Sol xhighopenai/gpt-5.6-sol
35.58
30.7%96.3%71/2313$55.983h 39m2.3Mcodex
2
Claude Opus 5 maxanthropic/claude-opus-5
32.57
28.1%88.0%65/23110$127.932h 34m4.5Mclaude
3
Claude Opus 5 mediumanthropic/claude-opus-5
28.36
24.7%70.5%57/23126$31.9647m 1s999.7Kclaude
4
GPT-5.6 Luna xhighopenai/gpt-5.6-luna
26.79
22.9%81.2%53/23113$24.593h 1m3.3Mcodex
5
GPT-5.6 Sol mediumopenai/gpt-5.6-sol
25.10
21.2%94.3%49/2313$17.9530m 52s703.0Kcodex
6
GPT-5.5 xhighopenai/gpt-5.5
21.20
17.7%95.5%41/2312$43.422h 22m2.2Mcodex
7
GPT-5.6 Terra xhighopenai/gpt-5.6-terra
19.21
16.0%95.3%37/2312$27.811h 45m2.1Mcodex
8
Kimi K3 highmoonshotai/kimi-k3
17.56
14.7%77.1%34/23111$12.381h 59m731.9Kpi
9
Grok 4.5 mediumxai/grok-4.5
16.54
13.9%73.3%32/23112$11.041h 37m909.6Kpi
10
Grok 4.5 highxai/grok-4.5
15.58
13.0%77.8%30/23110$5.601h 24m1.0Mpi
11
GPT-5.5 mediumopenai/gpt-5.5
12.63
10.4%92.3%24/2312$14.9424m 5s751.4Kcodex
12
GPT-5.6 Terra mediumopenai/gpt-5.6-terra
12.12
10.0%92.0%23/2312$5.1513m 15s617.7Kcodex
13
GPT-5.6 Luna mediumopenai/gpt-5.6-luna
12.08
10.0%82.8%23/2315$5.2311m 59s572.0Kcodex
14
Gemini 3.6 Flash mediumgoogle/gemini-3.6-flash
11.56
9.5%80.0%22/2316$10.7426m 21s2.7Mpi
15
Kimi K3 mediummoonshotai/kimi-k3
11.48
9.5%64.1%22/23114$10.841h 29m676.6Kpi
16
GLM-5.2 mediumzai/glm-5.2
10.46
8.7%62.5%20/23112$11.091h 3m1.5Mpi
17
GLM-5.2 highzai/glm-5.2
9.90
8.2%53.8%19/23118$51.842h 30m4.7Mpi
18
Gemini 3.6 Flash highgoogle/gemini-3.6-flash
8.99
7.4%77.3%17/2315$5.3322m 18s1.8Mpi
19
Claude Opus 4.8 maxanthropic/claude-opus-4.8
6.91
5.6%81.3%13/2313$7.5619m 29s80.8Kclaude
20
Claude Opus 4.8 mediumanthropic/claude-opus-4.8
6.88
5.6%61.9%13/2318$10.8118m 16s78.1Kclaude
21
Inkling highthinkingmachines/inkling
6.32
5.2%48.0%12/23113$1.9311m 34s300.9Kpi
22
Inkling mediumthinkingmachines/inkling
5.26
4.3%37.0%10/23117$2.1810m 31s509.0Kpi
23
Claude Haiku 4.5 defaultanthropic/claude-haiku-4.5
4.73
3.9%33.3%9/23118$5.9129m 40s912.4Kclaude
24
Gemini 3.5 Flash Lite mediumgoogle/gemini-3.5-flash-lite
2.14
1.7%44.4%4/2315$0.581m 46s459.9Kpi
25
Gemini 3.5 Flash Lite highgoogle/gemini-3.5-flash-lite
1.07
0.9%28.6%2/2315$0.181m 7s406.5Kpi