GLM-4.6V (Reasoning): benchmark results
GLM-4.6V evaluated with reasoning enabled. Provider: Zhipu. Released 2025-12-09. Access: Open.
Unified ELO 1512 ± 1, rank #793 of 1761 rated models, from 40 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Writing | 39.66 | Writing Score | 72.1 |
| UGI - Natural Intelligence | 28.9 | NatInt Score | 71.1 |
| AA Omniscience | -26.95 | Score | 58.7 |
| AA Global-MMLU-Lite - English | 90.25 | Accuracy (%) | 53.2 |
| AA Humanity's Last Exam | 9.64 | Accuracy (%) | 52.7 |
| AA Terminal-Bench Hard | 14.39 | Accuracy (%) | 51.3 |
| AA GPQA Diamond | 71.92 | Accuracy (%) | 51.2 |
| AA Global-MMLU-Lite - Korean | 83.75 | Accuracy (%) | 50.5 |
| Artificial Analysis Intelligence Index | 10.73 | Intelligence Index | 49 |
| AA Global-MMLU-Lite - Swahili | 72.25 | Accuracy (%) | 48.2 |
| AA Global-MMLU-Lite - Yoruba | 52.08 | Accuracy (%) | 47.7 |
| AA Global-MMLU-Lite - French | 86.25 | Accuracy (%) | 46.8 |
Interactive version: theaggregate.ai/model?slug=glm-4-6v-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.