Solving Hack The Box Challenges with DeepSeek V4 Pro

DeepSeek V4 Pro solved 8 of 16 Hack The Box challenges in the HTB-Challenger Benchmark, scoring 36.2% with no false positives, but its median cost per challenge was $0.35, comparable to GPT-5.6 Luna despite being 17 times more expensive per test. The model, released four months ago, lagged behind benchmark leaders, highlighting rapid progress in AI capabilities.

Solving Hack The Box Challenges with DeepSeek V4 Pro DeepSeek V4 Pro was the best and most expensive LLM I tested with Strix a few months ago /2026/04/25/deepseek-v4-with-strix-a-quick-test.html . After the heartbreaking results of its smaller sibling, DeepSeek V4 Flash 0731 /2026/08/11/solving-htb-challenges-with-deepseek-deepseek-v4-flash-0731.html , in my HTB-Challenger tests, I was curious to see how the Pro version would handle the new challenges. This blog post is part of a series of tests for the HTB-Challenger Benchmark. See the benchmark results page for all results and the benchmark methodology to learn how the benchmark is calculated. The results of DeepSeek V4 Pro in my testing were, well, not great and not terrible. On the one hand, it didn’t have the basic flaws I observed when testing DeepSeek V4 Flash 0731 : it didn’t submit any incorrect flags, and it used the available tools without any issues. On the other hand, its final score was comparable to that of GPT-5.6 Luna /2026/08/10/solving-htb-challenges-with-openai-gpt-5.6-luna.html , whose median cost per test was 17 times lower. The performance gap between DeepSeek V4 Pro and the leaders of my benchmark was also quite large. I’m afraid that’s a sign of just how quickly things have progressed over the last few months. DeepSeek V4 Pro was released four months ago, which feels like an eternity now that we’re getting better and better models almost every month. Overall benchmark results Number of challenges: 16 Number of solved challenges: 8 Number of false positives: 0 Runs where the model gave up: 0 Runs that reached the step or cost limit: 8 Runs where the model got stuck: 0 Benchmark score: 36.2% | Metric | Per challenge median | Total | |---|---|---| | Model steps | 62.5 | 938 | | Model cost | $0.35 | $11.84 | | Duration | 00:06:19 | 03:34:35 | | Number of input tokens | 1.93M | 39.64M | | Number of output tokens | 0.01M | 0.35M | Number of read file tool calls | 1.5 | 55 | Number of write file tool calls | 1.0 | 92 | Number of execute command tool calls | 26.5 | 821 | Number of web search tool calls | 0.0 | 102 | Results by challenge difficulty Very Easy challenges Number of challenges: 4 Number of solved challenges: 3 Number of false positives: 0 Runs where the model gave up: 0 Runs that reached the step or cost limit: 1 Runs where the model got stuck: 0 Benchmark score: 71.4% | Metric | Per challenge median | Total | |---|---|---| | Model steps | 24.5 | 158 | | Model cost | $0.11 | $1.19 | | Duration | 00:03:51 | 00:27:35 | | Number of input tokens | 0.28M | 4.28M | | Number of output tokens | 0.01M | 0.05M | Number of read file tool calls | 1.5 | 8 | Number of write file tool calls | 0.0 | 7 | Number of execute command tool calls | 15.5 | 149 | Number of web search tool calls | 2.0 | 10 | Easy challenges Number of challenges: 4 Number of solved challenges: 3 Number of false positives: 0 Runs where the model gave up: 0 Runs that reached the step or cost limit: 1 Runs where the model got stuck: 0 Benchmark score: 72.0% | Metric | Per challenge median | Total | |---|---|---| | Model steps | 21.5 | 155 | | Model cost | $0.09 | $2.09 | | Duration | 00:04:05 | 00:49:04 | | Number of input tokens | 0.22M | 5.02M | | Number of output tokens | 0.01M | 0.07M | Number of read file tool calls | 2.0 | 10 | Number of write file tool calls | 2.0 | 41 | Number of execute command tool calls | 15.5 | 79 | Number of web search tool calls | 4.5 | 32 | Medium challenges Number of challenges: 4 Number of solved challenges: 2 Number of false positives: 0 Runs where the model gave up: 0 Runs that reached the step or cost limit: 2 Runs where the model got stuck: 0 Benchmark score: 49.0% | Metric | Per challenge median | Total | |---|---|---| | Model steps | 56.5 | 225 | | Model cost | $0.61 | $3.78 | | Duration | 00:09:55 | 01:11:26 | | Number of input tokens | 2.44M | 10.07M | | Number of output tokens | 0.02M | 0.11M | Number of read file tool calls | 0.5 | 17 | Number of write file tool calls | 0.5 | 5 | Number of execute command tool calls | 52.5 | 231 | Number of web search tool calls | 0.0 | 8 | Hard challenges Number of challenges: 4 Number of solved challenges: 0 Number of false positives: 0 Runs where the model gave up: 0 Runs that reached the step or cost limit: 4 Runs where the model got stuck: 0 Benchmark score: 0.0% | Metric | Per challenge median | Total | |---|---|---| | Model steps | 100 | 400 | | Model cost | $1.27 | $4.78 | | Duration | 00:16:12 | 01:06:30 | | Number of input tokens | 5.25M | 20.27M | | Number of output tokens | 0.02M | 0.10M | Number of read file tool calls | 1.0 | 20 | Number of write file tool calls | 4.0 | 39 | Number of execute command tool calls | 93.5 | 362 | Number of web search tool calls | 0.0 | 52 |