Compare / Claude Haiku 4.5 vs Phi 4
Claude Haiku 4.5 vs Phi 4
19 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Haiku 4.5 | Phi 4 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,420 | 1,256 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,387 | 1,210 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,452 | 1,268 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,415 | 1,245 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,414 | 1,256 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,399 | 1,229 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 95.3% | 87.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 54.4% | 24.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 53.6% | 3.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 68.7% | 28.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 62.5% | 50.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 86.5% | 69.6% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 78.7% | 60.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 83.5% | 4.5% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 6.0% | 19.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.39 | 0.34 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 52.2 | 25.7 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.5% | 80.7% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 9.8% | 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.