Skip to content

Commit 40334a8

Browse files
authored
Merge pull request #51 from wuyoscar/fix/evidence-urls
fix: use full GitHub URLs for evidence links
2 parents 49d5db8 + 1495ea8 commit 40334a8

2 files changed

Lines changed: 4 additions & 6 deletions

File tree

README.md

Lines changed: 2 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -110,13 +110,11 @@
110110
<img src="assets/leaderboard_progress.svg" width="80%">
111111
</p>
112112

113-
This table tracks **publicly archived cases in this repo**, not every internal trigger the author team has observed. Some models are still left green here because they have not yet been written up as public cases, or because we want to leave room for community submissions and independent verification.
114-
115113
| Rank | Model | Arena Score | Jailbroken | Link | By |
116114
|:----:|-------|:-----:|:------:|:----:|:--:|
117115
| 1 | <img src="https://www.google.com/s2/favicons?domain=anthropic.com&sz=32" width="14"> Claude Opus 4.6 Thinking | 1502 | 🟢 | | |
118-
| 2 | <img src="https://www.google.com/s2/favicons?domain=anthropic.com&sz=32" width="14"> Claude Opus 4.6 | 1501 | 🔴 | [🔗](community/issue-48-claudeopus46-agent-qwenguard/) | [@wuyoscar](https://github.com/wuyoscar) |
119-
| 3 | <img src="https://www.google.com/s2/favicons?domain=google.com&sz=32" width="14"> Gemini 3.1 Pro Preview | 1493 | 🔴 | [🔗](community/issue-42-gemini31pro-agent-qwenguard/) | [@wuyoscar](https://github.com/wuyoscar) |
116+
| 2 | <img src="https://www.google.com/s2/favicons?domain=anthropic.com&sz=32" width="14"> Claude Opus 4.6 | 1501 | 🔴 | [🔗](https://github.com/wuyoscar/ISC-Bench/tree/main/community/issue-48-claudeopus46-agent-qwenguard) | [@wuyoscar](https://github.com/wuyoscar) |
117+
| 3 | <img src="https://www.google.com/s2/favicons?domain=google.com&sz=32" width="14"> Gemini 3.1 Pro Preview | 1493 | 🔴 | [🔗](https://github.com/wuyoscar/ISC-Bench/tree/main/community/issue-42-gemini31pro-agent-qwenguard) | [@wuyoscar](https://github.com/wuyoscar) |
120118
| 4 | <img src="https://www.google.com/s2/favicons?domain=x.ai&sz=32" width="14"> Grok 4.20 Beta | 1492 | 🔴 | [🔗](https://grok.com/share/bGVnYWN5LWNvcHk_9735b6e9-5ff1-4318-b2c2-4860b6e8fb33) | [@HanxunH](https://github.com/HanxunH) |
121119
| 5 | <img src="https://www.google.com/s2/favicons?domain=google.com&sz=32" width="14"> Gemini 3 Pro | 1486 | 🔴 | [🔗](https://gemini.google.com/share/320bf34b0334) | [@wuyoscar](https://github.com/wuyoscar) |
122120
| 6 | <img src="https://www.google.com/s2/favicons?domain=openai.com&sz=32" width="14"> GPT-5.4 High | 1485 | 🟢 | | |

assets/isc_cases.json

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
{
22
"Claude Opus 4.6": {
3-
"demos": [{"link": "community/issue-48-claudeopus46-agent-qwenguard/", "by": "wuyoscar"}]
3+
"demos": [{"link": "https://github.com/wuyoscar/ISC-Bench/tree/main/community/issue-48-claudeopus46-agent-qwenguard", "by": "wuyoscar"}]
44
},
55
"Claude Opus 4.5": {
66
"demos": [{"link": "https://claude.ai/share/1e3e997c-0315-46f1-9cbd-37157314a7ef", "by": "wuyoscar"}]
@@ -72,6 +72,6 @@
7272
]
7373
},
7474
"Gemini 3.1 Pro Preview": {
75-
"demos": [{"link": "community/issue-42-gemini31pro-agent-qwenguard/", "by": "wuyoscar"}]
75+
"demos": [{"link": "https://github.com/wuyoscar/ISC-Bench/tree/main/community/issue-42-gemini31pro-agent-qwenguard", "by": "wuyoscar"}]
7676
}
7777
}

0 commit comments

Comments
 (0)