Compare / Claude Sonnet 4.5 vs gemini-3-pro-preview
Claude Sonnet 4.5 vs gemini-3-pro-preview
13 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Sonnet 4.5 | gemini-3-pro-preview |
|---|---|---|---|
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 95.0% | 85.6% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 65.0% | 61.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 61.4% | 63.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 73.2% | 72.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 68.8% | 75.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 88.7% | 90.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 81.1% | 83.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 81.0% | 80.0% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 5.0% | 33.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.41 | 0.37 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 66.9 | 66.7 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 95.6% | 99.4% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 12.0% | 13.6% |
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.