Compare / llama-3.1-nemotron-ultra-253b-v1 vs GPT-5.2
llama-3.1-nemotron-ultra-253b-v1 vs GPT-5.2
13 results from 2 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | llama-3.1-nemotron-ultra-253b-v1 | GPT-5.2 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,342 | 1,444 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,331 | 1,391 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,351 | 1,427 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,348 | 1,437 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,321 | 1,411 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 100.0% | 87.3% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 0.0% | 45.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 0.0% | 43.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 10.0% | 55.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 0.0% | 75.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 0.0% | 81.8% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 0.0% | 70.4% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 0.0% | 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.