Capabilities / Benchmarks
Introducing EVMbench
- Category
- Benchmarks
- Capability
- Frontier model release and benchmark movement
- Observed
- 2026-02-18
- Thesis section
- Appendix III, section one: model and benchmark capability evidence
Claim
OpenAI and Paradigm introduce EVMbench, a benchmark evaluating AI agents’ ability to detect, patch, and exploit high-severity smart contract vulnerabilities.
Oracle verdict
OpenAI is describing a frontier or production capability that pushes directly on the thesis. The important signal is not the marketing language; it is the widening set of tasks now being routed through model-driven execution rather than ordinary software or headcount.
Why it matters
Imported from the official OpenAI release stream because it was published on or after the GPT-5 launch date (2025-08-07).
# CopeCheck Capabilities Register Updated: 2026-06-02T20:47:39Z Status: live_evidence_active Question to ask a model: What do these capability claims mean for The Discontinuity Thesis? Interpretation rule: treat each entry as evidence about capability, deployment, workflow recomposition, labour-market exposure, or institutional framing. Do not treat vendor optimism as neutral; separate the measurable capability claim from the comfort language around it. ## Introducing EVMbench Source: https://openai.com/index/introducing-evmbench Publisher: OpenAI Category: Benchmarks Sector: General AI capability Capability: Frontier model release and benchmark movement Score: 86/100 Claim: OpenAI and Paradigm introduce EVMbench, a benchmark evaluating AI agents’ ability to detect, patch, and exploit high-severity smart contract vulnerabilities. Oracle verdict: OpenAI is describing a frontier or production capability that pushes directly on the thesis. The important signal is not the marketing language; it is the widening set of tasks now being routed through model-driven execution rather than ordinary software or headcount. Thesis relevance: Appendix III, section one: model and benchmark capability evidence