Compare / ministral-8b-2410 vs GPT-4.1
ministral-8b-2410 vs GPT-4.1
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 | ministral-8b-2410 | GPT-4.1 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,235 | 1,415 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,222 | 1,402 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,238 | 1,405 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,211 | 1,403 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,238 | 1,415 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,226 | 1,405 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 100.0% | 86.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 4.5% | 23.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 0.0% | 38.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 11.1% | 54.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 0.0% | 100.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 0.0% | 88.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 0.0% | 78.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 1.0% | 68.0% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.9% | 99.9% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 7.4% | 5.6% |
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.