token.app › Compare › GPT-5.2 vs GLM 5.2
GPT-5.2 vs GLM 5.2
GPT-5.2 leads on 4 of 6 shared benchmarks. GLM 5.2 is 12× cheaper per token on a blended 3:1 basis. GLM 5.2 accepts the larger context window (1.0M).
Head to head
Blended price uses a 3:1 input:output mix
| GPT-5.2 | GLM 5.2 | |
|---|---|---|
| Provider | OpenAI | Zhipu AI |
| Input $/1M | $1.75 | $0.252 |
| Output $/1M | $14.00 | $0.792 |
| Blended $/1M | $4.81 | $0.387 |
| Context window | 400K | 1.0M |
| Max output | 128K | 128K |
| Released | Dec 2025 | Jun 2026 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 91.4% | 91.9% |
| SWE-bench Verified | 73.8% | 78.7% |
| FrontierMath T1–3 | 67.4% | 59.2% |
| FrontierMath T4 | 31.7% | 29.3% |
| SimpleQA Verified | 38.9% | 38.1% |
| OTIS Mock AIME | 96.1% | 86.4% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose GPT-5.2 if…
- Higher FrontierMath T1–3 (67.4% vs 59.2%)
- Higher FrontierMath T4 (31.7% vs 29.3%)
- Higher SimpleQA Verified (38.9% vs 38.1%)
- Higher OTIS Mock AIME (96.1% vs 86.4%)
Choose GLM 5.2 if…
- Costs less per token — $0.387 vs $4.81 blended
- Higher GPQA Diamond (91.9% vs 91.4%)
- Higher SWE-bench Verified (78.7% vs 73.8%)
- Larger context window (1.0M)
- Open weights — self-hostable
- Newer model (released Jun 2026)
FAQ
Which is better, GPT-5.2 or GLM 5.2?
Across the 6 benchmarks both models have independently-run scores for, GPT-5.2 leads on 4 and GLM 5.2 leads on 2. Benchmarks are one input — price and context window are on this page too.
Is GPT-5.2 cheaper than GLM 5.2?
GLM 5.2 is cheaper: $0.387 versus $4.81 per million tokens blended at 3:1 input:output. Input alone: $1.75 vs $0.252. Output alone: $14.00 vs $0.792.
What context windows do GPT-5.2 and GLM 5.2 have?
GPT-5.2: 400,000 tokens. GLM 5.2: 1,048,576 tokens.
Who makes GPT-5.2 and GLM 5.2?
GPT-5.2 is made by OpenAI. GLM 5.2 is made by Zhipu AI.