Up to four models
GLM-5.2 vs Kimi K2.7 Code
On the index (GPT-4 = 100), GLM-5.2 scores 154 and Kimi K2.7 Code 151. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
154138–169
WeightsOpen
ReleasedJun 2026
Price in / out$0.0070 / $6.8
Context1.05M
Core tests taken6 of 9
Kimi K2.7 Code
151135–167
WeightsOpen
ReleasedJun 2026
Price in / out$0.70 / $3.75
Context262K
Core tests taken3 of 9
GLM-5.2 and Kimi K2.7 Code are too close to call (3 points apart, within the uncertainty), ahead on 3 of 3 shared core tests, at a similar price.
Test by testthird-party results
Every result as a table
| Test | GLM-5.2 | Kimi K2.7 Code |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 91.9% | 87.9% |
| LiveBench Data Analysis | 73.7% | 62.7% |
| LiveBench IF | 62.3% | 56.3% |
| LiveBench Language | 76.2% | 77.9% |
| LiveBench Reasoning | 78.6% | 82.8% |
| SimpleBench | 58.8% | 57.9% |
| SimpleQA Verified | 34.2% | 36.5% |
| Maths | ||
| FrontierMath (tiers 1-3) | 59.2% | 54.0% |
| AIME-style maths (OTIS mock) | 86.4% | 95.6% |
| LiveBench Mathematics | 89.8% | 79.6% |
| Chess puzzles | 22.0% | 14.0% |
| FrontierMath (tier 4) | 29.3% | 12.2% |
| Surface Evolver Bench | 55.6% | 48.8% |
| Coding | ||
| LiveBench Agentic Coding | 51.8% | 45.7% |
| LiveBench Coding | 79.7% | 74.0% |
| Code Migration | 37.9% | 25.4% |
| LiveCodeBench | 69.5% | 82.0% |
| ProgramBench | 0.5% | 0.0% |
| SWE-bench | 82.8% | 78.2% |
| Vibe Code Bench v1.1 | 64.0% | 47.2% |
| DeepSWE | 43.8% | 30.5% |
| WeirdML | 70.1% | 54.1% |
| Agents | ||
| APEX-Agents | 45.2% | 37.6% |
| SkillsBench | 45.1% | 50.0% |
Tests at least two of these models have taken. Bold rows are the core tests.