GLM-5 vs Kimi K3
GLM-5 (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 158 vs 146).
- GLM-5 is cheaper on input tokens — $0.70 vs $2.10 per 1M.
- Kimi K3 has a larger context window (1M vs 205K tokens).
- Kimi K3 ranks higher for coding (97th vs 41th percentile).
| Attribute | GLM-5 | Kimi K3 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 146 | 158 |
| Coding | 41 | 97 |
| Math | 20 | 82 |
| Reasoning & Knowledge | 30 | 73 |
| Agentic & Tools | 58 | 80 |
| Specifications | ||
| Developer | Z.ai (Zhipu AI) | Moonshot |
| Family | — | Kimi |
| Released | Feb 12, 2026 | Jul 16, 2026 |
| Parameters | 744B | 2.8T |
| Availability | Open weights (unrestricted) | Open weights (non-commercial) |
| Context window | 205K | 1M |
| Price — $/M input | $0.70 | $2.10 |
| Price — $/M output | $2.24 | $10.95 |
| Inputs | text | text, image, video |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 80% | 97% |
| APEX | 17% | 39% |
| ARC-AGI | 45% | 95% |
| ARC-AGI-2 | 5% | 60% |
| FrontierMath | 16% | — |
| FrontierMath Tier 4 | 2% | — |
| GPQA Diamond | 88% | 93% |
| Humanity's Last Exam | 29% | 47% |
| SciCode | 46% | 60% |
| SimpleBench | 53% | 61% |
| SWE-bench Verified | 72% | — |
| Terminal-Bench | 52% | — |
| WebDev Arena | 1435 | 1674 |
| WeirdML | 48% | 83% |
| τ²-bench | 98% | — |
| SimpleQA Verified | — | 51% |
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 better than Kimi K3?
On Epoch AI's Capabilities Index, Kimi K3 scores higher (158) than GLM-5 (146). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is cheaper, GLM-5 or Kimi K3?
GLM-5 is cheaper on input tokens at $0.70 per million, versus $2.10 (representative OpenRouter pricing).
Which has a larger context window, GLM-5 or Kimi K3?
Kimi K3 supports up to 1M tokens, compared with 205K for the other.
Which is better for coding, GLM-5 or Kimi K3?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Kimi K3 ranks higher — 97th vs 41th 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.