Z.AI
availableShows if the model has enough results for an index.GLM-4.5-Air
GLM-4.5-Air is a non-reasoning model from Z.AI. 8 benchmarks count toward its score, in 4 categories.
IndexOverall score. 50 is the middle.36.5 ±10.2
CoverageShare of the index weight with results.55%
SpeedOutput tokens per second.42/s
Input / 1MUS dollars per 1M input tokens.$0.13
Output / 1MUS dollars per 1M output tokens.$0.85
ContextMaximum tokens in one request.131K
EloLMArena rating and rank.1384 (#155)
50 is the middle of the board. The range shows the doubt in the index.
30,367 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
8 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result on the index scale. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| Artificial Analysis GPQA Diamond | Knowledge | 73.3% | 43.7 | — | — | Artificial Analysis |
| Artificial Analysis Long Context Reasoning | Reasoning | 46.7% | 40.6 | — | — | Artificial Analysis |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 46.5% | 32.2 | — | — | Victor Barres et al. |
| Artificial Analysis IFBench | Instruction | 37.6% | 27.3 | — | — | Artificial Analysis |
| Artificial Analysis Omniscience Accuracy | Knowledge | 16.3% | 34.0 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 11.1% | 36.3 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 7.0% | 32.2 | — | — | Artificial Analysis |
| Critical Physics Tasks | Reasoning | 0.0% | 38.4 | — | — | Artificial Analysis |
8 benchmarks count, from 8 of 8 results. A grey row does not count. Too few models took that benchmark.