Compare / Claude Opus 4.5 vs granite-3.1-8b-instruct
Claude Opus 4.5 vs granite-3.1-8b-instruct
14 results from 2 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Opus 4.5 | granite-3.1-8b-instruct |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,472 | 1,225 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,469 | 1,171 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,503 | 1,236 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,483 | 1,193 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,474 | 1,208 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,467 | 1,180 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 90.8% | 80.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 73.8% | 14.4% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 68.4% | 7.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 77.5% | 27.1% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 68.8% | 68.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 89.7% | 78.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 79.8% | 60.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 84.5% | 0.5% |
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.