Compare / Llama 3.1 8B Instruct vs Phi 4
Llama 3.1 8B Instruct 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 | Llama 3.1 8B Instruct | Phi 4 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,210 | 1,256 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,177 | 1,210 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,198 | 1,268 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,191 | 1,245 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,211 | 1,256 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,182 | 1,229 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 42.7% | 87.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 10.8% | 24.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 25.8% | 28.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 93.8% | 50.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 84.0% | 69.6% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 70.8% | 60.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 3.0% | 4.5% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 20.0% | 19.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.34 | 0.34 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 24.8 | 25.7 |
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.