benchmark evidence
SimpleQA Factual Accuracy
Factual accuracy on 4,326 short-form questions from OpenAI SimpleQA.
activeupstream source ->
winner on SimpleQA Factual Accuracy
OpenAI: o142.6
direct benchmark result, not a broad vertical composite | source row dated 2000-01-01
scored on 2000-01-01 · stale source data (9646d)
latest mapped results | top 20
| # | Model | Score | Evidence | Tested |
|---|---|---|---|---|
| 1 | OpenAI: o1 | 42.6 | model-only vendor_claim | 2000-01-01 |
| 2 | OpenAI: GPT-4.1 | 41.6 | model-only vendor_claim | 2000-01-01 |
| 3 | OpenAI: o3 Mini | 13.4 | model-only vendor_claim | 2000-01-01 |
what this result means
Factual accuracy on 4,326 short-form questions from OpenAI SimpleQA.
This benchmark contributes direct public evidence. Read its scope before generalizing the result.
A win here is a win on SimpleQA Factual Accuracy. Broad task pages require independent corroboration before naming a general winner.
source record
category: reasoning
metric: percent_correct
matched models: 3
latest source date: 2000-01-01
direction: higher is better