Xentir GLM-5.2 vs Kimi K2.6
GLM-5.2 OPEN WEIGHTS · Z.ai (Zhipu AI), released 2026-06-16
Kimi K2.6 OPEN WEIGHTS · Moonshot, released 2026-04-20
“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-09-09 · Methodology · Data Sources
Neither model leads on more of the 6 benchmarks where both are measured — GLM-5.2 on 3, Kimi K2.6 on 3. The remaining 3 of 9 tracked benchmarks cannot be compared: 2 have a result for only one of the two models, 1 for neither. Nothing on this page is estimated to fill those in.
Head-to-head
Measured on 6 of 9 tracked benchmarks for both models — GLM-5.2 leads on 3, Kimi K2.6 leads on 3.
| Benchmark | GLM-5.2 | Kimi K2.6 | Leads |
|---|---|---|---|
| Epoch Capabilities Index (ECI) | 151.9 | 151.0 | GLM-5.2 |
| SWE-bench Verified | 0.787 (max) | 0.767 | GLM-5.2 |
| GPQA Diamond | 0.919 (max) | 0.908 | GLM-5.2 |
| MATH Level 5 | Not measured | Not measured | Not measured on both |
| OTIS Mock AIME 2024-2025 | 0.864 (max) | 0.961 | Kimi K2.6 |
| FrontierMath | Not measured | 0.390 | Comparison unavailable — GLM-5.2 has no published result |
| FrontierMath Tier 4 | Not measured | 0.146 | Comparison unavailable — GLM-5.2 has no published result |
| SimpleQA Verified | 0.342 (max) | 0.349 | Kimi K2.6 |
| Chess Puzzles | 0.210 (max) | 0.260 | Kimi K2.6 |
What remains uncertain
- GLM-5.2 has no published result on FrontierMath, FrontierMath Tier 4.
- 1 tracked benchmark has no published result for either model.
A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.