Agentic & Tool Use benchmark

# ExploitBench leaderboard

> ExploitBench results for 9 AI models, led by Claude Mythos Preview at 73.8%. What the benchmark measures, who runs it, and a source for every score.
- Canonical page: https://noometry.com/benchmarks/exploitbench
- Last updated: 2026-10-10
- Title: ExploitBench Leaderboard (October 2026): Scores by Model

As of October 2026, Claude Mythos Preview has the highest published ExploitBench score on Noometry at 73.8%, out of 9 models with results.

Last verified October 10, 2026

## About ExploitBench

A description with primary sources is being prepared for this benchmark.

- **Category:** [Agentic & Tool Use](https://noometry.com/best/agentic)
- **Introduced:** 2026
- **Unit:** Percent (random guessing ≈ 0%)
- **Official site:** [epoch.ai](https://epoch.ai/benchmarks)

## Top 9 models

Top models on ExploitBench

1.  Claude Mythos Preview 73.8%
2.  GPT-5.5 47.4%
3.  Claude Opus 4.7 26.5%
4.  Gemini 3.1 Pro Preview 26.1%
5.  Claude Sonnet 4.6 23.6%
6.  Kimi K2.6 18.4%
7.  GLM-5.1 18.1%
8.  Claude Haiku 4.5 13.7%
9.  MiniMax-M2.7 13.3%
10.  020406080

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## All results

ExploitBench results by model
| # | Model | Provider | Score | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- | --- |
| 1 | [Claude Mythos Preview](https://noometry.com/models/claude-mythos-preview) | [Anthropic](https://noometry.com/providers/anthropic) | 73.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 2 | [GPT-5.5](https://noometry.com/models/gpt-5-5) | [OpenAI](https://noometry.com/providers/openai) | 47.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 3 | [Claude Opus 4.7](https://noometry.com/models/claude-opus-4-7) | [Anthropic](https://noometry.com/providers/anthropic) | 26.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 4 | [Gemini 3.1 Pro Preview](https://noometry.com/models/gemini-3-1-pro-preview) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 26.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 5 | [Claude Sonnet 4.6](https://noometry.com/models/claude-sonnet-4-6) | [Anthropic](https://noometry.com/providers/anthropic) | 23.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 6 | [Kimi K2.6](https://noometry.com/models/kimi-k2-6) | [Moonshot AI](https://noometry.com/providers/moonshot) | 18.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 7 | [GLM-5.1](https://noometry.com/models/glm-5-1) | [Z.ai (Zhipu)](https://noometry.com/providers/zai) | 18.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 8 | [Claude Haiku 4.5](https://noometry.com/models/claude-haiku-4-5) | [Anthropic](https://noometry.com/providers/anthropic) | 13.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 9 | [MiniMax-M2.7](https://noometry.com/models/minimax-m2-7) |  [![](/logos/minimax.svg) MiniMax](https://noometry.com/providers/minimax) | 13.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

## Compare the leaders

-   [Claude Mythos Preview vs GPT-5.5](https://noometry.com/compare/claude-mythos-preview-vs-gpt-5-5)
-   [Claude Mythos Preview vs Claude Opus 4.7](https://noometry.com/compare/claude-mythos-preview-vs-claude-opus-4-7)
-   [Claude Mythos Preview vs Gemini 3.1 Pro Preview](https://noometry.com/compare/claude-mythos-preview-vs-gemini-3-1-pro-preview)
-   [Claude Mythos Preview vs Claude Sonnet 4.6](https://noometry.com/compare/claude-mythos-preview-vs-claude-sonnet-4-6)
-   [GPT-5.5 vs Claude Opus 4.7](https://noometry.com/compare/claude-opus-4-7-vs-gpt-5-5)
-   [GPT-5.5 vs Gemini 3.1 Pro Preview](https://noometry.com/compare/gemini-3-1-pro-preview-vs-gpt-5-5)

## Other agentic & tool use benchmarks

-   [Terminal-Bench](https://noometry.com/benchmarks/terminal-bench)
-   [APEX-Agents](https://noometry.com/benchmarks/apex-agents)
-   [Berkeley Function Calling Leaderboard](https://noometry.com/benchmarks/bfcl)
-   [OSWorld 2.0](https://noometry.com/benchmarks/osworld-2)
-   [GDPval](https://noometry.com/benchmarks/gdpval)
-   [Remote Labor Index](https://noometry.com/benchmarks/remote-labor-index)
-   [TheAgentCompany](https://noometry.com/benchmarks/the-agent-company)
-   [τ²-bench Airline](https://noometry.com/benchmarks/tau2-airline)
-   [τ²-bench Banking](https://noometry.com/benchmarks/tau2-banking)
-   [τ²-bench Retail](https://noometry.com/benchmarks/tau2-retail)
-   [τ²-bench Telecom](https://noometry.com/benchmarks/tau2-telecom)
-   [Cybench](https://noometry.com/benchmarks/cybench)

## Frequently asked questions

### Which model has the highest ExploitBench score?

As of October 2026, Claude Mythos Preview has the highest published ExploitBench score on Noometry at 73.8%, out of 9 models with results.

### What is the best open-weight model on ExploitBench?

Kimi K2.6 has the highest ExploitBench accuracy among open-weight models at 18.4%, ranking 6 of 9 overall.

### Cite this page

Noometry. (2026). ExploitBench leaderboard. Retrieved October 10, 2026, from https://noometry.com/benchmarks/exploitbench

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/benchmarks/exploitbench.md).