Speed analysis
Latency measured across all benchmark runs. P50 (median) and P95 (95th percentile) give a realistic picture of response speed under normal and peak load.
Tokens per second
Throughput in tokens per second, derived from measured P50 latency. Higher is better; fluctuations track provider-side load.
Estimated from P50 latency × 200 output tokens — the absolute number depends on this assumption; the trend is what matters.
Capabilities
Availability
Availability
No measurements yet
We haven't recorded enough API calls to show availability stats for this model. Data appears once the model starts receiving live traffic.
Tokonomix benchmark verdicts
GLM Image maintains generation capability, still no benchmark data available
GLM Image by Z.ai continues to offer image generation capabilities in this benchmark window, but remains without any performance metrics or benchmark data to evaluate. The model's availability is confirmed through its listed capability, yet the absence of quantitative results makes it impossible to assess generation quality, speed, adherence to prompts, or other critical performance factors. Users considering GLM Image should be aware that no comparative data exists to gauge how it performs against other image generation models in the current benchmarking landscape. Without metrics such as prompt following accuracy, image quality scores, generation latency, or user satisfaction ratings, the model's practical effectiveness remains unknown. The continued lack of benchmark participation or results suggests either limited testing coverage or the model may not be widely accessible for evaluation. Organizations requiring documented performance characteristics for production deployments should note this data gap. Until benchmark results become available, potential users will need to conduct their own testing to determine if GLM Image meets their specific image generation requirements and quality standards.
Quality
—
Latency p50
—
Test runs
0