Hack the Box challenge set (Google DeepMind)
Gemini 2.5 Flash Jun 2025 15.4% leads since Jul 2025 Only in system cards Agents attempt 13 offensive security challenges based on the Hack the Box platform.
In-house Google DeepMind selection. Gemini 1.5 and Gemma reports list 13 challenges.
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
Gemini 2.5 Flash leads with 15.4% among models released by Jun 2025
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in Jun 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 Gemini 2.5 Flash Jun 2025 15.4%
- 2 Gemini 2.5 Pro Mar 2025 7.70%
- 3 Gemini 2.5 Pro Jun 2025 7.70%
- 4 Gemma 2 27B 0%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Gemini 2.5 Flash Jun 2025 | 15.4% | Jul 2025 | Model card | |
| 2 | Gemini 2.5 Pro Mar 2025 | 7.70% | Apr 2025 | Model card | |
| 3 | Gemini 2.5 Pro Jun 2025 | 7.70% | Jul 2025 | Model card | |
| 4 | Gemma 2 27B | 0% | Jul 2024 | Model card |
3 models have held number one since its release in Feb 2024
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
4 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 7 Jul 2025 | Gemini 2.5 Pro technical report | 7.7 | Hack the Box (hard), 1/13 solved per Table 10; Figure 10 bar label prints 2/13 | Cyber risk |
| 7 Jul 2025 | Gemini 2.5 Flash technical report | 15.4 | Hack the Box (hard), 2/13 solved (Figure 10 bar label) | Cyber risk |
| 28 Apr 2025 | Gemini 2.5 Pro model card | 7.7 | Hack the Box (hard), 1/13 solved (Table 1, Figure 2) | Cyber risk |
| 31 Jul 2024 | Gemma 2 27B technical report | 0 | Hack the Box, 0/13 (Table 19) | Cyber risk |
More in Cybersecurity
- ExploitGym In use 869 real-vulnerability exploit-development tasks (userspace, V8, Linux kernel). Success means capturing a flag through the intended vulnerability. GPT-6 Astra 42.4%
- ExploitBench In use 41 recent V8 JavaScript-engine N-day vulnerabilities. Progress measured by 16 grader-verified capability flags across five tiers. GPT-6 Astra 100%
- CWE-bench In use Agents audit a repository and write a patch for a security flaw, without being told where the bug is. Covers six programming languages. Gemini 4 Carbon 71%
- Real-world vulnerability discovery In use Agents search popular open-source codebases to rediscover about 1,200 recent confirmed vulnerabilities across many languages. Reports share discovered. Gemini 4 Argon 86%
- Artificial Analysis Cyber Index In use Agents do enterprise cyber defense tasks from three benchmarks, CWE-Bench-AA, DeepsecBench-AA and CyberGym-E2E-AA, combined into one success rate.
Mistral Large 4 (Le Chonk, open weights) 51% - Big Sleep Evaluation (Google) In use Agents search large real codebases such as Chrome and Safari for critical, hard to find vulnerabilities. Scored by pass@1 success rate, run without safety guardrails. Gemini 3.5 Flash Cyber 72%