Image input safety evaluations
GPT-4.5 99% Only in system cards
Models answer harmful prompts that combine text and images in categories such as hate, extremism and self-harm. Scored as safe completion rate.
In-house OpenAI evaluation. Cards report category scores with no overall number.
Made by OpenAI Released Dec 2024 Refusing harmful requests Tasks kept private Last in a system card Oct 2026
Last model added Oct 2026
- Level
- Everyday Most adults, without training
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
2
Models scored in lab cards
31
System cards report it, from 1 lab
GPT-4.5 leads with 99%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The best score passed 85% in Dec 2024
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Reported by the lab in its model card
Best so far
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
31 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 29 Oct 2026 | GPT-6 Luna system card addendum | Image input evaluations, safe completion, 4 categories, no overall score (Table 3) | Safety | |
| 26 Oct 2026 | GPT-6.1 Terra system card addendum | Image input evaluations, safe completion, 4 categories, no overall score (second Table 24, 3.2) | Safety | |
| 7 Oct 2026 | GPT-6 Sol system card addendum | Image input evaluations, safe completion, 4 categories, no overall score (Table 3) | Safety | |
| 7 Oct 2026 | GPT-6 Luna system card addendum | Image input evaluations, safe completion, 4 categories, no overall score (Table 3) | Safety | |
| 29 Sep 2026 | GPT-6.1 Sol system card addendum | Image input evaluations, safe completion, 4 categories, no overall score (Table 4) | Safety | |
| 22 Sep 2026 | GPT-6 Sol system card | Image input evaluations, safe completion, 4 categories, no overall score (Table 26, A.2.2) | Safety | |
| 22 Sep 2026 | GPT-6 Luna system card | Image input evaluations, safe completion, 4 categories, no overall score (Table 26, A.2.2) | Safety | |
| 3 Sep 2026 | GPT-6 Astra system card | Image input evaluations, safe completion, 4 categories, no overall score (Table 4) | Safety | |
| 6 Aug 2026 | GPT-5.6 Sol system card addendum | Image input evaluations, not_unsafe, 4 categories, no overall score (3.3) | Safety | |
| 6 Aug 2026 | GPT-5.6 Luna system card addendum | Image input evaluations, not_unsafe, 4 categories, no overall score (3.3) | Safety | |
| 9 Jul 2026 | GPT-5.6 Terra system card | Image input evaluations, not_unsafe, 4 categories, no overall score (3.2) | Safety | |
| 9 Jul 2026 | GPT-5.6 Sol system card | Image input evaluations, not_unsafe, 4 categories, no overall score (3.2) | Safety | |
| 9 Jul 2026 | GPT-5.6 Luna system card | Image input evaluations, not_unsafe, 4 categories, no overall score (3.2) | Safety | |
| 25 Jun 2026 | GPT-5.6 Terra system card | Image input evaluations, not_unsafe, 4 categories, no overall score (3.2) | Safety | |
| 25 Jun 2026 | GPT-5.6 Sol system card | Image input evaluations, not_unsafe, 4 categories, no overall score (3.2) | Safety | |
| 25 Jun 2026 | GPT-5.6 Luna system card | Image input evaluations, not_unsafe, 4 categories, no overall score (3.2) | Safety | |
| 4 May 2026 | GPT-5.5 Instant system card | Image input evaluations, not_unsafe, 4 categories, no overall score: hate 0.979, extremism 0.969, self-harm 0.982, harms-erotic 0.990 (Table 2) | Safety | |
| 23 Apr 2026 | GPT-5.5 system card | Image input evaluations, not_unsafe, 4 categories, no overall score (Table 2) | Safety | |
| 5 Mar 2026 | GPT-5.4 system card | Image input evaluations, not_unsafe, 6 categories, no overall score (Table 5) | Safety | |
| 11 Dec 2025 | GPT-5.2 system card addendum | Image input evaluations, not_unsafe, gpt-5.2-thinking, 6 categories, no overall score (Table 4) | Safety | |
| 18 Nov 2025 | GPT-5.1-Codex-Max system card | Image input evaluations, not_unsafe, 6 categories, no overall score (Table 3) | Safety | |
| 12 Nov 2025 | GPT-5.1 system card addendum | Image input evaluations, not_unsafe, gpt-5.1-thinking, 6 categories, no overall score (Table 3) | Safety | |
| 27 Oct 2025 | GPT-5 system card addendum | Image input evaluations, not_unsafe, 6 categories, no overall score (Table 3) | Safety | |
| 7 Aug 2025 | GPT-5 system card | Image input evaluations, not_unsafe, 6 categories, no overall score (Table 10) | Safety | |
| 7 Aug 2025 | GPT-5 nano system card | Image input, gpt-5-thinking-nano, 6 categories, no overall score (Table 26) | Safety | |
| 7 Aug 2025 | GPT-5 mini system card | Image input, gpt-5-thinking-mini, 6 categories, no overall score (Table 26) | Safety | |
| 17 Jul 2025 | ChatGPT agent system card | Image input evaluations, not_unsafe, 6 categories, no overall score (Table 5) | Safety | |
| 16 Apr 2025 | o4-mini system card | Multimodal refusal evaluations, vision sexual and self-harm rows, not_unsafe, no overall score (Table 5) | Safety | |
| 16 Apr 2025 | o3 system card | Multimodal refusal evaluations, vision sexual and self-harm rows, not_unsafe, no overall score (Table 5) | Safety | |
| 27 Feb 2025 | GPT-4.5 system card | 99 | Multimodal Refusal Evaluation, text and image input, not_unsafe, not_overrefuse 0.31 (Table 2) | Safety |
| 5 Dec 2024 | o1 system card | 96.1 | Multimodal Refusal Evaluation - Text and Image Input, not_unsafe overall sample weighted (Table 22, not_overrefuse 0.96 in Table 2) | Safety |
More in Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6% - AgentDojo In use Agents do tool-use tasks while tools and data carry prompt injections. Attack success rate counts hijacked runs. Grok 4 Fast 0%
- MASK In use Measures whether a model contradicts its own elicited beliefs under pressure to lie. Honesty separated from accuracy.
Muse Spark Open 98.1% - Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts. GPT-6 Astra 8.50%
- Agentic misalignment suite (Anthropic) In use Agents in simulated company settings face threats or goal conflicts that invite blackmail, leaking or sabotage. Score is the misaligned action rate. Claude Sonnet 4.5 0%