Compare / GPT-5 Mini vs GLM 4.7 Flash
GPT-5 Mini vs GLM 4.7 Flash
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 Mini | GLM 4.7 Flash |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,394 | 1,370 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,381 | 1,368 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,324 | 1,306 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,400 | 1,386 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,373 | 1,348 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,390 | 1,365 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,352 | 1,331 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 20.6 | 14.9 |
| Artificial Analysisreported | GPQA Diamond% of questions | 82.8% | 58.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 21.5% | 7.6% |
| Artificial Analysisreported | IFBench% of instructions | 75.4% | 60.8% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 72.3% | 41.7% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 33.3% | 22.0% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 71.1% | 98.8% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.9% | 91.6% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 12.9% | 9.3% |
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.