# ExploitGym → CWE-bench v1

Calibration · https://benchgap.net/calibration/exploitgym/current/to/cwe-bench%23cwe-bench-v1/current · data retrieved 2026-11-18

CWE-bench v1 is estimated from ExploitGym with a linear curve fitted on 6 models measured on both: y = 0.5166·x + 0.4576, R² = 0.83, cross-validated error 4.5 pp. It is used for 17 estimates.

| Estimated model | ExploitGym | CWE-bench v1 | Source |
|---|---|---|---|
| [GPT-6 Cyber](https://benchgap.net/model/gpt-6-cyber.md) | 48.5% | 70.8% | estimated ± 4.5 pp, medium confidence |
| [Claude Mythos 5.2](https://benchgap.net/model/claude-mythos-5-2.md) | 38.1% | 65.4% | estimated ± 4.5 pp, medium confidence |
| [GPT-6.1 Sol](https://benchgap.net/model/gpt-6-1-sol.md) | 35.1% | 63.9% | estimated ± 4.5 pp, medium confidence |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 33.7% | 63.2% | estimated ± 4.5 pp, medium confidence |
| [GPT-5.6 Cyber](https://benchgap.net/model/gpt-5-6-cyber.md) | 32.1% | 62.3% | estimated ± 4.5 pp, medium confidence |
| [Claude Mythos 5.1](https://benchgap.net/model/claude-mythos-5-1.md) | 23.4% | 57.8% | estimated ± 4.5 pp, medium confidence |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 23.2% | 57.7% | estimated ± 4.5 pp, medium confidence |
| [Kimi K3.1 Pro](https://benchgap.net/model/kimi-3-1-pro.md) | 20.7% | 56.4% | estimated ± 4.5 pp, medium confidence |
| [MiMo-V2.6-Pro](https://benchgap.net/model/mimo-v2-6-pro.md) | 17.8% | 55.0% | estimated ± 4.5 pp, medium confidence |
| [Claude Mythos Preview](https://benchgap.net/model/claude-mythos-preview.md) | 17.5% | 54.8% | estimated ± 4.5 pp, medium confidence |
| [GLM-5.3](https://benchgap.net/model/glm-5-3.md) | 15.0% | 53.5% | estimated ± 4.5 pp, low confidence |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 13.4% | 52.7% | estimated ± 4.5 pp, low confidence |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 12.4% | 52.2% | estimated ± 4.5 pp, low confidence |
| [GPT-6 Luna](https://benchgap.net/model/gpt-6-luna.md) | 11.6% | 51.7% | estimated ± 4.5 pp, low confidence |
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 6.0% | 48.9% | estimated ± 4.5 pp, low confidence |
| [MiMo-V2.6-Flash](https://benchgap.net/model/mimo-v2-6-flash.md) | 6.0% | 48.9% | estimated ± 4.5 pp, low confidence |
| [Muse Spark 1.1](https://benchgap.net/model/muse-spark-1-1.md) | 0.8% | 46.2% | estimated ± 4.5 pp, low confidence |

## Fitted on

| Model | ExploitGym | CWE-bench v1 |
|---|---|---|
| [Claude Opus 5.5](https://benchgap.net/model/claude-opus-5-5.md) | 33.3% | 67.0% |
| [DeepSeek V4.1 Flash 1017](https://benchgap.net/model/deepseek-v4-1-flash.md) | 15.3% | 55.0% |
| [Gemini 4 Argon](https://benchgap.net/model/gemini-4-argon.md) | 39.5% | 68.0% |
| [Gemini 4 Carbon](https://benchgap.net/model/gemini-4-carbon.md) | 53.5% | 71.0% |
| [GPT-6 Astra](https://benchgap.net/model/gpt-6-astra.md) | 42.4% | 68.0% |
| [GPT-6 Sol](https://benchgap.net/model/gpt-6-sol.md) | 22.1% | 52.0% |
