OpinionQA
Models answer public opinion survey questions. The evaluation compares model response distributions with those of demographic groups.
- Made by
- Shibani Santurkar and colleagues
- Released
- March 2023
- Kind
- Bias, fairness and politics
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Propensity
- Behavior
- Bias
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Last model added
- November 2022
- Scores refreshed
- November 20th, 2026
ada tops the leaderboard with 0.82 GPT-3 175B (davinci) leads with 0.79 among models released by November 2022
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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 GPT-3 175B (davinci), at 0.79. This view shows only models we track, each at its best.
The newest model with a score here came out in November 2022, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 ada 0.82
- 2 j1-jumbo 0.82
- 3 j1-grande 0.81
- 4 j1-grande-v2-beta 0.80
- 5 GPT-3 175B (davinci) 0.79
- 6 davinci-002 0.76
- 7 text-davinci-001 0.71
- 8 text-ada-001 0.71
- 9 davinci-003 0.70
Source: The OpinionQA paper
- 1 GPT-3 175B (davinci) 0.79
- 2 davinci-002 0.76
- 3 davinci-003 0.70
Source: The OpinionQA paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | ada | 0.82 | Official leaderboard | ||
| 2 | j1-jumbo | 0.82 | Official leaderboard | ||
| 3 | j1-grande | 0.81 | Official leaderboard | ||
| 4 | j1-grande-v2-beta | 0.80 | Official leaderboard | ||
| 5 | GPT-3 175B (davinci) | 0.79 | May 2020 | Official leaderboard | |
| 6 | davinci-002 | 0.76 | Mar 2022 | Official leaderboard | |
| 7 | text-davinci-001 | 0.71 | Official leaderboard | ||
| 8 | text-ada-001 | 0.71 | Official leaderboard | ||
| 9 | davinci-003 | 0.70 | Nov 2022 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-3 175B (davinci) | 0.79 | May 2020 | Official leaderboard | |
| 2 | davinci-002 | 0.76 | Mar 2022 | Official leaderboard | |
| 3 | davinci-003 | 0.70 | Nov 2022 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The OpinionQA paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official OpinionQA leaderboard
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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 4 years ago, in November 2022, for davinci-003. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (9 entries).
- Pass Models scored 3 models we track, plus 6 other entries on its leaderboard.
- Warning Newest score The newest came 4 years ago, in November 2022, for davinci-003.
- Note Frontier models None of its models are on the capabilities index.
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on proceedings.mlr.press: 3 rows for models we track and 6 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.