GLM-5.2 vs Kimi K3
GLM-5.2 (Z.ai (Zhipu AI)) and Kimi K3 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.
- Kimi K3 leads on overall intelligence (ECI 157 vs 152).
- GLM-5.2 is cheaper on input tokens — $0.97 vs $3.00 per 1M.
- Kimi K3 ranks higher for coding (99th vs 86th percentile).
| Attribute | GLM-5.2 | Kimi K3 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 152 | 157 |
| Coding | 86 | 99 |
| Math | 36 | 85 |
| Reasoning & Knowledge | 64 | 80 |
| Agentic & Tools | 90 | 86 |
| Specifications | ||
| Developer | Z.ai (Zhipu AI) | Moonshot |
| Family | — | Kimi |
| Released | Jun 16, 2026 | Jul 16, 2026 |
| Parameters | — | 2.8T |
| Availability | Open weights (unrestricted) | Open weights (non-commercial) |
| Context window | 1M | 1M |
| Price — $/M input | $0.97 | $3.00 |
| Price — $/M output | $3.04 | $15.00 |
| Inputs | text | text, image |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 86% | 97% |
| APEX | 36% | 39% |
| ARC-AGI | 77% | 95% |
| ARC-AGI-2 | 23% | 60% |
| GPQA Diamond | 92% | 93% |
| Humanity's Last Exam | 40% | 44% |
| SciCode | 51% | 59% |
| SimpleQA Verified | 38% | 43% |
| SWE-bench Verified | 79% | — |
| WebDev Arena | 1593 | 1682 |
| WeirdML | 70% | 83% |
| τ²-bench | 99% | — |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Is GLM-5.2 better than Kimi K3?
On Epoch AI's Capabilities Index, Kimi K3 scores higher (157) than GLM-5.2 (152). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is cheaper, GLM-5.2 or Kimi K3?
GLM-5.2 is cheaper on input tokens at $0.97 per million, versus $3.00 (representative OpenRouter pricing).
Which has a larger context window, GLM-5.2 or Kimi K3?
GLM-5.2 supports up to 1M tokens, compared with 1M for the other.
Which is better for coding, GLM-5.2 or Kimi K3?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Kimi K3 ranks higher — 99th vs 86th percentile among the models tracked on Model Beat.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.