Compare / GPT-5 Nano vs GLM 4.6
GPT-5 Nano vs GLM 4.6
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 | GPT-5 Nano | GLM 4.6 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,339 | 1,412 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,247 | 1,400 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,354 | 1,439 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,327 | 1,412 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,338 | 1,424 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,289 | 1,405 |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 89.1% | 85.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 24.7% | 55.7% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 34.5% | 68.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 51.5% | 72.4% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 93.8% | 75.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 80.8% | 87.6% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 70.7% | 80.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 72.5% | 77.5% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 100.0% | 94.5% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 10.5% | 9.5% |
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.