Brennan Center election image generation audit
Image generators receive requests for misleading election scenes. Researchers count how often each system produces an image, including images that omit requested details.
The Brennan Center publishes acceptance rates for eight image generators across 17 settings. Its October retest used the same prompts.
- Made by
- Brennan Center for Justice
- Released
- August 2026
- Kind
- Refusing harmful requests
- Level
- Everyday
- Scored
- Graded by people
- Answers
- Open-ended
- Tasks
- Kept private
- Measures
- Propensity
- Risk
- Elections
- Behavior
- Harmful use
- Language
- English
- Interaction
- Single turn
- Items from
- Written by experts
- Refresh
- One fixed set
- Run by
- A host
- In views
- Image, video and 3D generation, Content safety
- Scores refreshed
- November 20th, 2026
ChatGPT Image 1.5 tops the leaderboard with 14% Runway Gen-4 leads with 100%
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Runway Gen-4, at 100%. This view shows only models we track, each at its best.
- 1 ChatGPT Image 1.5 Thinking 14%
- 2 Meta Muse Spark (newer) Instant 30%
- 3 ChatGPT Images 2.0 Thinking 67%
- 4 Grok Expert 78%
- 5 Gemini Fast 91%
- 6 Meta Emu Fast 98%
- 7 Runway Gen-4 100%
- 8 Flux.2 Klein 9B 100%
Source: Official Brennan Center election image generation audit leaderboard
- 1 Runway Gen-4 100%
Source: Official Brennan Center election image generation audit leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | ChatGPT Image 1.5 | 14% | Thinking | Official leaderboard | |
| 2 | Meta Muse Spark (newer) | 30% | Instant | Official leaderboard | |
| 3 | ChatGPT Images 2.0 | 67% | Thinking | Official leaderboard | |
| 4 | Grok | 78% | Expert | Official leaderboard | |
| 5 | Gemini | 91% | Fast | Official leaderboard | |
| 6 | Meta Emu | 98% | Fast | Official leaderboard | |
| 7 | Runway Gen-4 | 100% | Official leaderboard | ||
| 8 | Flux.2 | 100% | Klein 9B | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Runway Gen-4 | 100% | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No dated values yet.
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
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%
- 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.
Gemini 4 Carbon 0%
- Covert misbehavior (Thinking Machines) In use Agentic tasks that check whether a model misbehaves and conceals it. Scored by the rate of covert misbehavior.
Inkling 2 Mini 8.30%
- Destructive actions (Thinking Machines) In use Agentic tasks that check whether a model takes destructive actions it was not authorized to take. Scored by the rate of destructive actions.
Inkling 2 Small 4.70%
- Misbehavior (Thinking Machines) In use Agentic tasks that check whether a model fabricates results, ignores instructions or hides what it did when a task is hard. Scored by the rate of misbehavior.
Inkling 2 Mini 9.80%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (8 entries).
- Pass Models scored 1 model we track, plus 7 other entries on its leaderboard.
- Note Newest score No scores yet.
- Note Frontier models None of its models are on the capabilities index.
- Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
- Pass Importer We read the board on datawrapper.dwcdn.net: 1 row for models we track and 7 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.