GLM-4.5 vs Kimi-k1.5: Specs & Benchmark Comparison
| Characteristic | GLM-4.5 | Kimi-k1.5 |
|---|---|---|
| Company | Zhipu AI | Moonshot AI |
| Release Date | July 27, 2025 | January 20, 2025 |
| Parameters | 355B | — |
| Multimodal | No | Yes |
| Context (input) | 131K | — |
| Context (output) | 98K | — |
| Input Price / 1M | $0.60 | — |
| Output Price / 1M | $2.20 | — |
| Average Score | 0.8 | 0.8 |
| Benchmarks | ||
| AIME 2024 | 0.9 | 0.8 |
| MATH-500 | 1.0 | 1.0 |
Visual Benchmark Comparison
GLM-4.5
Kimi-k1.5
AIME 20240.9 vs 0.8
0.9
0.8
MATH-5001.0 vs 1.0
1.0
1.0
Verdict
GLM-4.5 leads in 1 out of 2 comparison categories.
Overall Performance
Both models show comparable average scores: GLM-4.5 — 0.8, Kimi-k1.5 — 0.8.
Recency
GLM-4.5 is newer: released 7/27/2025 vs 1/20/2025.
More About These Models
Related Comparisons
Frequently Asked Questions
Which is better for coding — GLM-4.5 or Kimi-k1.5?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — GLM-4.5 or Kimi-k1.5?
API pricing data is available on the individual model pages.
Which has a larger context window — GLM-4.5 or Kimi-k1.5?
Context window data is available on the individual model pages.
The GLM-4.5 and Kimi-k1.5 comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the GLM-4.5 or Kimi-k1.5 page. See also the complete list of AI model comparisons.