Compare / GPT-5 Nano vs GLM 5.1
GPT-5 Nano vs GLM 5.1
14 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 5.1 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,339 | 1,465 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,247 | 1,448 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,354 | 1,495 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,327 | 1,460 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,338 | 1,465 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,289 | 1,453 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 13.0 | 26.1 |
| Artificial Analysisreported | GPQA Diamond% of questions | 67.6% | 86.8% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 9.5% | 30.1% |
| Artificial Analysisreported | IFBench% of instructions | 67.6% | 76.3% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 45.0% | 73.7% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 17.4% | 43.2% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 36.5% | 97.7% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 11.7% | 34.0% |
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.