GLM 4.6V
GLM / Z.ai
23scores
13benchmarks
$0.3 / $0.9 per 1M tokenscost in/out
Metadata
GLM Open source
Aliases: glm-4.6-20251208, glm-4.6v, z-ai-glm-4.6-20251208, z-ai-glm-4.6v, z-ai/glm-4.6-20251208, z-ai/glm-4.6v
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| Tau2-Bench Telecom | Agentic | 234 | 31.6% | 2026-05-11 |
| Tau2-Bench Telecom | Agentic | 239 | 30.7% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 181 | 14.4% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 299 | 3% | 2026-05-11 |
| OpenUGI | Alignment | 573 | 34.72 | 2026-05-06 |
| OpenUGI | Alignment | 729 | 32.04 | 2026-05-06 |
| SciCode | Coding | 244 | 30.4% | 2026-05-11 |
| SciCode | Coding | 292 | 27.2% | 2026-05-11 |
| From Perception to Action | Embodied AI | 14 | 7.3% | 2026-05-28 |
| Artificial Analysis Intelligence Index | Intelligence | 210 | 23.42 | 2026-05-11 |
| Artificial Analysis Intelligence Index | Intelligence | 285 | 17.1 | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 172 | 8.9% | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 442 | 3.7% | 2026-05-11 |
| MathVision | Intelligence | 37 | 63.50 | 2026-05-06 |
| MMLU-Pro | Intelligence | 116 | 79.9% | 2026-05-11 |
| MMLU-Pro | Intelligence | 174 | 75.2% | 2026-05-11 |
| AIME 2025 | Math | 45 | 85.3% | 2026-05-11 |
| AIME 2025 | Math | 194 | 26.3% | 2026-05-11 |
| MMLongBench-Doc | Multimodal | 9 | 54.90 | 2026-05-06 |
| GPQA Diamond | Reasoning | 187 | 71.9% | 2026-05-11 |
| GPQA Diamond | Reasoning | 305 | 56.6% | 2026-05-11 |
| CritPt | Science | 207 | 0% | 2026-05-11 |
| CritPt | Science | 208 | 0% | 2026-05-11 |
No matching rows.