Compare / gemini-3-pro-preview vs GPT-5 Mini
gemini-3-pro-preview vs GPT-5 Mini
11 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-pro-preview | GPT-5 Mini |
|---|---|---|---|
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 85.6% | 91.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 61.7% | 44.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 63.1% | 27.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 72.5% | 55.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 75.0% | 93.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 90.7% | 69.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 83.1% | 62.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 80.0% | 82.0% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.4% | 99.9% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 13.6% | 12.9% |
| Vending-Bench 2reported | Money after a yearUS dollars | $5,478.16 | $-31.18 |
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.