GLM 4.5 Air
GLM / Z.ai
27scores
26benchmarks
$0 / $0 per 1M tokenscost in/out
Metadata
GLM Open source
Aliases: glm-4.5-air, glm-4.5-air:free, z-ai-glm-4.5-air, z-ai/glm-4.5-air, z-ai/glm-4.5-air:free
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| Galileo Agent Leaderboard | Agentic | 9 | 0.44 | 2026-05-06 |
| MCP-Universe | Agentic | 22 | 19.48 | 2026-05-06 |
| PinchBench | Agentic | 22 | 0.86 | 2026-05-06 |
| Tau2-Bench Telecom | Agentic | 186 | 46.5% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 145 | 20.5% | 2026-05-11 |
| OpenUGI | Alignment | 185 | 46.50 | 2026-05-06 |
| OpenUGI | Alignment | 798 | 30.62 | 2026-05-06 |
| SciCode | Coding | 242 | 30.6% | 2026-05-11 |
| NeoEvalPlusN | Creative | 60 | 15.75 | 2026-05-06 |
| AI Energy Score | Efficiency | 98 | 5 | 2026-05-06 |
| Vectara HHEM Hallucination Leaderboard | Factuality | 47 | 90.70 | 2026-05-06 |
| BenchLM | General Knowledge | 108 | 19 | 2026-05-06 |
| HELM AIR-Bench | Generalization | 61 | 0.570864 | 2026-05-28 |
| Artificial Analysis Intelligence Index | Intelligence | 214 | 23.17 | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 217 | 6.8% | 2026-05-11 |
| MMLU-Pro | Intelligence | 85 | 81.5% | 2026-05-11 |
| AIME 2025 | Math | 62 | 80.7% | 2026-05-11 |
| MATH-500 | Mathematics | 4 | 0.98 | 2026-05-06 |
| LiveMedBench | Medical | 19 | 0.1105 | 2026-05-27 |
| Medmarks | Medical | 24 | 0.5410241342400426 | 2026-05-27 |
| Design Arena | Multimodal | 65 | 1196 | 2026-05-06 |
| Artificial Analysis Openness Index | Openness | 28 | 55.56 | 2026-05-11 |
| GPQA Diamond | Reasoning | 174 | 73.3% | 2026-05-11 |
| Humanity's Last Exam (Text Only) | Reasoning | 29 | 9.41 | 2026-05-06 |
| MultiNRC | Reasoning | 39 | 10.43 | 2026-05-06 |
| CritPt | Science | 203 | 0% | 2026-05-11 |
| BFCL-v3 | Tool Use | 2 | 0.76 | 2026-05-06 |
No matching rows.