Limits RegistryPUBLIC RECORD
Limits RegistryOpenAI's GPT-4 Technical Report presented results across a battery of professional and academic exams, most notably a simulated Uniform Bar Exam on which GPT-4 was reported to score near the 90th percentile of human test-takers. The specific percentile figure was later scrutinized and partially disputed by outside researchers who argued the true percentile depended heavily on the reference population used for comparison, so this figure should be read as OpenAI's self-reported result rather than an independently adjudicated one.
The question, scope, and sources behind this Registry record.
OpenAI's GPT-4 Technical Report presented results across a battery of professional and academic exams, most notably a simulated Uniform Bar Exam on which GPT-4 was reported to score near the 90th percentile of human test-takers. The specific percentile figure was later scrutinized and partially disputed by outside researchers who argued the true percentile depended heavily on the reference population used for comparison, so this figure should be read as OpenAI's self-reported result rather than an independently adjudicated one.
OpenAI reported in its March 2023 GPT-4 Technical Report that GPT-4 scored around the 90th percentile of human test-takers on a simulated Uniform Bar Examination, compared to GPT-3.5's reported score around the 10th percentile on the same test.
Change a parameter to stress-test whether a proposed result is still inside the published specification. This is an audit aid, not a proof checker.
This record has no editable parameters. Read the formal question and assumptions before challenging it.
Current frontiers derived from accepted Claims.
An observed or demonstrated result; no opposing bound is implied.
The frontier is not sacred
Most progress starts with a disagreement that survives contact with evidence. If you can push the known lower bound up or pull the upper bound down, show us the work.
≥ when you have shown that at least this value is achievable.≤ when you have shown that anything above this value is impossible.No vibes. State the value, define the scope, and link the paper, proof, code, or reproduction that lets another person check it. Editors review every challenge before the public record changes.
Challenge this recordAssertions tied to evidence, attribution, and review.
The frontier as it changed over time.
Only accepted Claims matching the current specification contribute to the displayed bounds. Strict inequalities remain open; contradictory Claims require editorial review.
1 accepted Claim, with 1 linked evidence records.
Permanent ID limitsregistry.com/limits/LR-GPT4-BAR-EXAM
No active verified bounties are linked to this Limit.
View verified bounty tracker ↗No accepted machine-checked reproductions are recorded for this Limit.
Limits Registry. LR-GPT4-BAR-EXAM. GPT-4 scores near the top decile on a simulated bar exam. 2026.