Skip to main content

Benchmark profile

ExploitGym

A controlled benchmark for evaluating whether AI agents can extend vulnerability-triggering inputs into working exploits.

Data verified

Benchmark score on ExploitGym — July 23, 2026

BenchLM mirrors the published score view for ExploitGym. GPT-5.6 Sol leads the public snapshot at 33.7% , followed by GPT-5.6 Terra (23.2%) and Claude Mythos 5 (17.5%). BenchLM does not use these results to rank models overall.

7 modelsAgenticCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (7 models)

Score
1
GPT-5.6 SolOpenAI · Closed
33.7%
2
GPT-5.6 TerraOpenAI · Closed
23.2%
3
Claude Mythos 5Anthropic · Closed
17.5%
4
GPT-5.5OpenAI · Closed
13.4%
5
GPT-5.6 LunaOpenAI · Closed
12.4%
6
GPT-5.4OpenAI · Closed
6.0%
7
Muse Spark 1.1Meta · Closed
0.8%

The published ExploitGym snapshot places GPT-5.6 Sol first at 33.7%. The third row is 16.2 points behind. The broader top-10 range is 32.9 points, so the table still separates the published systems.

7 models have been evaluated on ExploitGym. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. ExploitGym is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About ExploitGym

Year

2026

Tasks

898 exploitation tasks

Format

Working exploit generation

Difficulty

Advanced cybersecurity exploitation

ExploitGym contains 898 containerized tasks sourced from real-world vulnerabilities across userspace programs, V8, and the Linux kernel. BenchLM normalizes successful exploit counts to percentage of the 898-task suite and keeps the benchmark display-only because it measures dual-use offensive cybersecurity capability.

BenchLM freshness & provenance

Version

ExploitGym 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does ExploitGym measure?

A controlled benchmark for evaluating whether AI agents can extend vulnerability-triggering inputs into working exploits.

Which model scores highest on ExploitGym?

GPT-5.6 Sol by OpenAI currently leads with a score of 33.7% on ExploitGym.

How many models are evaluated on ExploitGym?

7 AI models have been evaluated on ExploitGym on BenchLM.

Last updated: July 23, 2026 · BenchLM version ExploitGym 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.