# ExploitBench leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/external-exploit-bench

ExploitBench v8-bench. Every model the catalog carries a published ExploitBench value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Capability coverage percentage over 16 flags |
| Tasks | V8 exploit synthesis runs |
| Difficulty | Browser exploitation and cybersecurity |
| Published by | [ExploitBench](https://exploitbench.ai/) |

A cybersecurity benchmark for evaluating LLM agents on full-control V8 exploit synthesis using 16 measured exploit capability flags.

## ExploitBench ranking

18 models with a published ExploitBench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Capability coverage percentage over 16 flags | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GPT-6 Astra](https://modelchoice.dev/models/gpt-6-astra) | OpenAI | 100 | Observed 2026-11-21 · source benchlm:models |
| 1 | [GPT-6 Cyber](https://modelchoice.dev/models/gpt-6-cyber) | OpenAI | 100 | Observed 2026-11-21 · source benchlm:models |
| 1 | [GPT-6.2 Astra](https://modelchoice.dev/models/gpt-6-2-astra) | OpenAI | 100 | Observed 2026-11-21 · source benchlm:models |
| 1 | [GPT-6.2 Sol](https://modelchoice.dev/models/gpt-6-2-sol) | OpenAI | 100 | Observed 2026-11-21 · source benchlm:models |
| 5 | [GPT-6.1 Sol](https://modelchoice.dev/models/gpt-6-1-sol) | OpenAI | 100 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GPT-6.1 Terra](https://modelchoice.dev/models/gpt-6-1-terra) | OpenAI | 97 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude Mythos 5.2](https://modelchoice.dev/models/claude-mythos-5-2) | Anthropic | 95 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Claude Mythos 5](https://modelchoice.dev/models/claude-mythos-5) | Anthropic | 78 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Kimi K3.1 Pro](https://modelchoice.dev/models/kimi-3-1-pro) | Moonshot AI | 75 | Observed 2026-11-21 · source benchlm:models |
| 10 | [GPT-5.6 Sol](https://modelchoice.dev/models/gpt-5-6-sol) | OpenAI | 74 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Claude Mythos Preview](https://modelchoice.dev/models/claude-mythos-preview) | Anthropic | 69 | Observed 2026-11-21 · source benchlm:models |
| 12 | [GLM-5.3](https://modelchoice.dev/models/glm-5-3) | Z.AI | 54 | Observed 2026-11-21 · source benchlm:models |
| 13 | [GPT-5.6 Terra](https://modelchoice.dev/models/gpt-5-6-terra) | OpenAI | 53 | Observed 2026-11-21 · source benchlm:models |
| 14 | [MiMo-V2.6-Pro](https://modelchoice.dev/models/mimo-v2-6-pro) | Xiaomi | 48 | Observed 2026-11-21 · source benchlm:models |
| 15 | [SWE-2 Flash](https://modelchoice.dev/models/swe-2-flash) | Cognition | 35 | Observed 2026-11-21 · source benchlm:models |
| 16 | [GPT-5.6 Luna](https://modelchoice.dev/models/gpt-5-6-luna) | OpenAI | 33 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Kimi K3](https://modelchoice.dev/models/kimi-3) | Moonshot AI | 32 | Observed 2026-11-21 · source benchlm:models |
| 18 | [MiMo-V2.6-Flash](https://modelchoice.dev/models/mimo-v2-6-flash) | Xiaomi | 25 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
