Compare / gpt-oss-120b vs GLM 4.5 Air
gpt-oss-120b vs GLM 4.5 Air
17 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-oss-120b | GLM 4.5 Air |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,385 | 1,395 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,351 | 1,372 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,277 | 1,327 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,357 | 1,390 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,323 | 1,361 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,352 | 1,373 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,309 | 1,341 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 11.6 | 11.1 |
| Artificial Analysisreported | GPQA Diamond% of questions | 78.2% | 73.3% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 19.6% | 7.0% |
| Artificial Analysisreported | IFBench% of instructions | 69.0% | 37.6% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 52.0% | 46.7% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 23.5% | 20.5% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 65.8% | 46.5% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 107.0% | 10.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.29 | 0.33 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 38.5 | 47.0 |
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.