Compare / Gemini 3 Flash Preview vs gpt-oss-120b
Gemini 3 Flash Preview vs gpt-oss-120b
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 | gpt-oss-120b |
|---|---|---|---|
| UGI Leaderboardreported | Requested-length error% off the requested word count | 16.0% | 107.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.37 | 0.29 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 67.7 | 38.5 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.8% | 99.9% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 13.5% | 14.2% |
| Vending-Bench 2reported | Money after a yearUS dollars | $3,634.72 | $-21.53 |
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.