Compare / Gemini 3.6 Flash vs GLM 4.5
Gemini 3.6 Flash vs GLM 4.5
13 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Gemini 3.6 Flash | GLM 4.5 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,472 | 1,412 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,469 | 1,372 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,500 | 1,444 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,473 | 1,405 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,482 | 1,411 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,472 | 1,382 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 34.0 | 12.8 |
| Artificial Analysisreported | GPQA Diamond% of questions | 92.8% | 78.2% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 40.8% | 13.0% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 80.0% | 52.7% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 9.0% | 13.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.33 | 0.36 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 69.8 | 57.3 |
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.