Compare / Gemini 2.5 Flash vs gemini-3-pro-preview
Gemini 2.5 Flash vs gemini-3-pro-preview
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 2.5 Flash | gemini-3-pro-preview |
|---|---|---|---|
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 93.7% | 85.6% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 41.3% | 61.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 36.2% | 63.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 56.2% | 72.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 75.0% | 75.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 88.1% | 90.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 78.2% | 83.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 62.0% | 80.0% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.0% | 99.4% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 7.8% | 13.6% |
| Vending-Bench 2reported | Money after a yearUS dollars | $548.84 | $5,478.16 |
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.