Compare / Gemini 2.5 Flash vs Phi 4
Gemini 2.5 Flash vs Phi 4
16 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 | Phi 4 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,399 | 1,256 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,394 | 1,210 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,424 | 1,268 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,400 | 1,245 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,409 | 1,256 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,402 | 1,229 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 93.7% | 87.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 41.3% | 24.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 36.2% | 3.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 56.2% | 28.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 75.0% | 50.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 88.1% | 69.6% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 78.2% | 60.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 62.0% | 4.5% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.0% | 80.7% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 7.8% | 3.7% |
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.