GLM-5.2 vs Qwen3.5 35B A3B: Specs & Benchmark Comparison
GLM-5.2 is developed by Zhipu AI, while Qwen3.5 35B A3B comes from Alibaba. Qwen3.5 35B A3B was released in March 2026, and GLM-5.2 followed 3 months later in June 2026. GLM-5.2 is the larger model at roughly 753 billion parameters, against 35 billion for Qwen3.5 35B A3B.
The two models share 3 published benchmarks. GLM-5.2 leads on 3 of them. The widest gaps are on Humanity's Last Exam, where GLM-5.2 scores 54.7% against 47.4%; GPQA, where GLM-5.2 scores 91.0% against 84.2%. Averaged across everything we track, GLM-5.2 sits at 60.9% and Qwen3.5 35B A3B at 69.0%.
GLM-5.2 is available through an API at $1.40 per million input tokens with a 1M-token context window. We do not track a hosted API for Qwen3.5 35B A3B, so pricing and context cannot be compared directly.
| Characteristic | GLM-5.2 | Qwen3.5 35B A3B |
|---|---|---|
| Company | Zhipu AI | Alibaba |
| Release Date | June 16, 2026 | March 1, 2026 |
| Parameters | 753B | 35B |
| Multimodal | No | No |
| Context (input) | 1.0M | — |
| Context (output) | 131K | — |
| Input Price / 1M | $1.40 | — |
| Output Price / 1M | $4.40 | — |
| Average Score | 60.9% | 69.0% |
| Benchmarks | ||
| Humanity's Last Exam | 54.7% | 47.4% |
| GPQA | 91.0% | 84.2% |
| HMMT 2025 | 94.0% | 89.0% |
Visual Benchmark Comparison
Verdict
GLM-5.2 leads in 1 out of 2 comparison categories.
Both models show comparable average scores: GLM-5.2 — 0.6, Qwen3.5 35B A3B — 0.7.
GLM-5.2 is newer: released 6/16/2026 vs 3/1/2026.
More About These Models
Related Comparisons
Frequently Asked Questions
Which is better for coding — GLM-5.2 or Qwen3.5 35B A3B?
Which model is cheaper — GLM-5.2 or Qwen3.5 35B A3B?
Which has a larger context window — GLM-5.2 or Qwen3.5 35B A3B?
The GLM-5.2 and Qwen3.5 35B A3B comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the GLM-5.2 or Qwen3.5 35B A3B page. See also the complete list of AI model comparisons.