Compare / GPT-5.4 Mini vs GLM 4.6
GPT-5.4 Mini vs GLM 4.6
19 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-5.4 Mini | GLM 4.6 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,447 | 1,447 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,460 | 1,412 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,402 | 1,400 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,480 | 1,439 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,434 | 1,412 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,447 | 1,424 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,424 | 1,405 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 56.1 | 45.8 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 24.1 | 18.5 |
| Artificial Analysisreported | GPQA Diamond% of questions | 87.5% | 78.0% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 28.1% | 14.5% |
| Artificial Analysisreported | IFBench% of instructions | 73.3% | 43.4% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 77.0% | 54.0% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 59.2% | 49.4% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 52.3% | 28.8% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 25.6% | 13.4% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 83.3% | 76.9% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 100.0% | 94.5% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 5.5% | 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.