Compare / Llama 3.2 1B Instruct vs Llama 3.2 3B Instruct
Llama 3.2 1B Instruct vs Llama 3.2 3B Instruct
17 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 3.2 1B Instruct | Llama 3.2 3B Instruct |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,070 | 1,146 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,083 | 1,145 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,082 | 1,179 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,086 | 1,146 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,111 | 1,167 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,076 | 1,143 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 51.6% | 52.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 3.2% | 6.2% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 0.0% | 4.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 10.8% | 21.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 43.8% | 87.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 38.4% | 82.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 11.8% | 58.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 0.0% | 1.0% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 22.0% | 31.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.33 | 0.36 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 11.8 | 10.4 |
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.