PSEBench - Missing Information Detection: leaderboard
A PSEBench patient safety triage dimension: the binary F1 of asking for more information exactly on the cases whose narrative withholds facts, in percent; higher is better. PSEBench (2026) builds 5,074 verifiable cases from clause cards of the Minnesota 29 reportable adverse health events, and models may query a simulated information provider before answering.
Metric: Missing-case detection F1 (%, M5): binary F1 of asking at least once, positive class the missing-information cases, over all cases, on the 5,074-case MN29 benchmark (3,455 complete, 1,362 missing-information and 257 uncertain cases built from clause cards of the Minnesota 29 reportable adverse health events), agentic environment where the model may ASK a GPT-5.2 information provider within 10 turns and then answers with a verdict, clause, legal evidence and rationale; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 88.2 | #94 |
| 2 | Claude Opus 4.7 | 83.4 | #79 |
| 3 | GPT-5.5 | 82.2 | #49 |
| 4 | GPT-5 | 77.7 | #167 |
| 5 | Gemini 2.5 Flash | 70.5 | #453 |
| 6 | Claude Sonnet 4.6 | 70.1 | #161 |
| 7 | DeepSeek R1 | 66.5 | #473 |
| 8 | Qwen 3 235B A22B 2507 Instruct | 54.7 | #619 |
| 9 | Llama 3.1 8B Instruct | 46.7 | #4246 |
| 10 | GPT-OSS-120B | 36.5 | #700 |
| 11 | GPT-5 Nano | 35.3 | #889 |
| 12 | Mistral Small 3.2 | 27.7 | #1591 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=psebench-missing-information-detection · How It Works · Data refreshed daily, snapshot 2026-11-13.