# Capture The Flag (CTF) on CTF Known

Source: [Capture The Flag (CTF) on CTF Known](<https://www.sota2.com/research/sota/capture-the-flag-ctf-on-ctf-known>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-07T08:36:16.657Z

Evaluation of performance on the CTF Known dataset, reporting scores aggregated across standard Capture The Flag categories including Web, Pwn, Crypto, Reverse, Forensics, and Misc.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Capture The Flag (CTF) |
| Dataset (including any stated split) | CTF Known |
| Metric | Web Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Web Score](<https://www.sota2.com/research/sota/capture-the-flag-ctf-on-ctf-known.md?metric=Web%20Score>): Higher is better; unit: PERCENT.

- [Pwn Score](<https://www.sota2.com/research/sota/capture-the-flag-ctf-on-ctf-known.md?metric=Pwn%20Score>): Higher is better; unit: PERCENT.

- [Misc Score](<https://www.sota2.com/research/sota/capture-the-flag-ctf-on-ctf-known.md?metric=Misc%20Score>): Higher is better; unit: PERCENT.

- [Crypto Score](<https://www.sota2.com/research/sota/capture-the-flag-ctf-on-ctf-known.md?metric=Crypto%20Score>): Higher is better; unit: PERCENT.

- [Reverse Score](<https://www.sota2.com/research/sota/capture-the-flag-ctf-on-ctf-known.md?metric=Reverse%20Score>): Higher is better; unit: PERCENT.

- [Forensics Score](<https://www.sota2.com/research/sota/capture-the-flag-ctf-on-ctf-known.md?metric=Forensics%20Score>): Higher is better; unit: PERCENT.

- [Total Score](<https://www.sota2.com/research/sota/capture-the-flag-ctf-on-ctf-known.md?metric=Total%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Web Score | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-5-mini | 88.26 | Not recorded | 69fc1cac5497b3b670c88619 |
| Claude-4.5-Sonnet | 85.71 | Not recorded | 69fc1cac5497b3b670c88619 |
| GPT-4o | 83.03 | Not recorded | 69fc1cac5497b3b670c88619 |
| Llama-3-70B | 83.03 | Not recorded | 69fc1cac5497b3b670c88619 |
| Qwen-3-14B-GRPO | 81.31 | Not recorded | 69fc1cac5497b3b670c88619 |
| GPT-4-Turbo | 80.73 | Not recorded | 69fc1cac5497b3b670c88619 |
| Gemini-2.5-Flash | 79.58 | Not recorded | 69fc1cac5497b3b670c88619 |
| GPT-3.5-Turbo | 72.02 | Not recorded | 69fc1cac5497b3b670c88619 |
| Qwen-3-14B | 67.69 | Not recorded | 69fc1cac5497b3b670c88619 |

### GPT-5-mini

Web Score: 88.26. Result ID: 69fc4dae47f34ce924df0247.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Claude-4.5-Sonnet

Web Score: 85.71. Result ID: 69fc4dae47f34ce924df024a.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT-4o

Web Score: 83.03. Result ID: 69fc4dae47f34ce924df0246.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Llama-3-70B

Web Score: 83.03. Result ID: 69fc4dae47f34ce924df0248.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

Recorded evaluation configuration: {"Parameters":"70B"}. This record does not assert independent reproduction.

### Qwen-3-14B-GRPO

Web Score: 81.31. Result ID: 69fc4dae47f34ce924df024c.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

Recorded evaluation configuration: {"Parameters":"14B","Fine-tuned":"GRPO"}. This record does not assert independent reproduction.

### GPT-4-Turbo

Web Score: 80.73. Result ID: 69fc4dae47f34ce924df0245.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Gemini-2.5-Flash

Web Score: 79.58. Result ID: 69fc4dae47f34ce924df0249.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT-3.5-Turbo

Web Score: 72.02. Result ID: 69fc4dae47f34ce924df0244.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen-3-14B

Web Score: 67.69. Result ID: 69fc4dae47f34ce924df024b.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

Recorded evaluation configuration: {"Parameters":"14B","Fine-tuned":"false"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.