GLM-5.2
Released Jun 2026. Open weights, available for self-hosting and fine-tuning.
GLM-5.2 is built by Zhipu AI and has 19 benchmark results tracked in the public leaderboard. It does not support multimodal input, with a context window of 1.05M tokens. At the blended 8:1 input-to-output rate, it costs $1.18 per million tokens.
Where GLM-5.2 ranks
The chart below ranks every model in the comparison by overall capability, which is the average of a model's scores across the eight workload axes. GLM-5.2 is the red bar. This is the single number to check first: it tells you where the model sits in the current pecking order before you dig into the detail.
Workload strengths
Each row below is the average normalized score across every benchmark tagged with that workload category. A higher number means the model performs better on that kind of task relative to the maximum possible score on those benchmarks. Categories where the model has no published results are shown as n/a.
| Workload | Index (0–1) |
|---|---|
| Reasoning | 80% |
| Coding | 52% |
| Agents | 60% |
| Math | 75% |
| Vision | 55% |
| Long Context | n/a |
| Writing | n/a |
| Knowledge | 91% |
How GLM-5.2 stacks up against every other model
Below is every head-to-head comparison involving GLM-5.2. Each card shows the win/loss tally across all workload axes and headline benchmarks. Tap any matchup for the full breakdown with per-benchmark scores, pricing, and workload recommendations.
GLM-5.2vs GPT-5.6 Sol
GPT-5.6 Sol leads 10–2
GLM-5.2vs Claude Opus 5
GLM-5.2 leads 5–4
GLM-5.2vs Kimi K3
Kimi K3 leads 8–2
GLM-5.2vs Claude Fable 5
GLM-5.2 leads 5–3
GLM-5.2vs GPT-5.6 Terra
GPT-5.6 Terra leads 10–2
GLM-5.2vs Qwen3.8 Max
Qwen3.8 Max leads 7–3
GLM-5.2vs Grok 4.5
GLM-5.2 leads 5–2
GLM-5.2vs DeepSeek-V4-Flash-0731
GLM-5.2 leads 6–1
GLM-5.2vs GPT-5.6 Sol
GPT-5.6 Sol leads 10–2
GLM-5.2vs Claude Opus 5
GLM-5.2 leads 5–4
GLM-5.2vs Kimi K3
Kimi K3 leads 8–2
GLM-5.2vs Claude Fable 5
GLM-5.2 leads 5–3
GLM-5.2vs GPT-5.6 Terra
GPT-5.6 Terra leads 10–2
GLM-5.2vs Qwen3.8 Max
Qwen3.8 Max leads 7–3
GLM-5.2vs Grok 4.5
GLM-5.2 leads 5–2
GLM-5.2vs DeepSeek-V4-Flash-0731
GLM-5.2 leads 6–1
GLM-5.2vs Claude Sonnet 5
Even at 5–5
GLM-5.2vs Claude Sonnet 5
Even at 5–5
Choose a matchup above, or start from the hub to pick any two models.