Compare / Gemini 3 Flash Preview vs o4 Mini
Gemini 3 Flash Preview vs o4 Mini
6 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Gemini 3 Flash Preview | o4 Mini |
|---|---|---|---|
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 66.8% | 19.6% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 16.0% | 19.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.37 | 0.33 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 67.7 | 46.9 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.8% | 98.7% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 13.5% | 18.6% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.