Compare / granite-3.1-8b-instruct vs GPT-5.2
granite-3.1-8b-instruct vs GPT-5.2
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 | granite-3.1-8b-instruct | GPT-5.2 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,225 | 1,444 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,171 | 1,391 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,236 | 1,475 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,193 | 1,427 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,208 | 1,437 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,180 | 1,411 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 80.0% | 87.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 14.4% | 45.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 7.5% | 43.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 27.1% | 55.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 68.8% | 75.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 78.3% | 81.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 60.3% | 70.4% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 0.5% | 75.5% |
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.