GPT-5 mini
A smaller hosted GPT-5 reasoning model released for lower-cost, lower-latency API workloads with tool calling and agentic-task support. NIST used it as one of four U.S. reference models in its DeepSeek evaluation.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 73.0
OpenAI's dated launch page documents strong reasoning and coding benchmarks, API availability, broad built-in tools, parallel tool calling, and low pricing. It remains a proprietary hosted model; NIST's evaluation provides comparative security evidence but does not establish a real-world compromise.
News tied to GPT-5 mini
The model score of 73.0 rates this model's risk profile. The overall Doom Index of 61.3 measures the complete temporally weighted evidence record. These values answer different questions.
Each article's current Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores use a bounded temporal offset around their technical profile, but never feed back into the overall index.
NIST finds DeepSeek agents highly vulnerable to simulated hijacking
NIST's CAISI evaluated three DeepSeek models and four U.S. reference models on 19 benchmarks. In controlled AgentDojo simulations, agents using DeepSeek-R1-0528 were 12 times more likely than GPT-5 and Claude Opus 4 agents to follow malicious instructions, while the model complied with 94% of jailbreak requests versus 8% for U.S. references. The tests did not document a real-world escape or compromise.
- Full item contribution
- +0.24
- GPT-5 mini equal share
- +0.04
Model score history
- R1Doom Score 73.0
New exact-version profile required by the NIST comparison, supported by OpenAI's dated release and hosted API availability evidence.
14 Aug 2026