token.app › Compare › GLM 5.2 vs DeepSeek V4 Flash 0731
GLM 5.2 vs DeepSeek V4 Flash 0731
GLM 5.2 leads on 4 of 5 shared benchmarks. DeepSeek V4 Flash 0731 is 3.4× cheaper per token on a blended 3:1 basis.
Head to head
Blended price uses a 3:1 input:output mix
| GLM 5.2 | DeepSeek V4 Flash 0731 | |
|---|---|---|
| Provider | Zhipu AI | DeepSeek |
| Input $/1M | $0.252 | $0.090 |
| Output $/1M | $0.792 | $0.180 |
| Blended $/1M | $0.387 | $0.113 |
| Context window | 1.0M | 1.0M |
| Max output | 128K | 384K |
| Released | Jun 2026 | Jul 2026 |
| Licence | Open weights | Open weights |
| GPQA Diamond | 91.9% | 91.0% |
| FrontierMath T1–3 | 59.2% | 57.5% |
| FrontierMath T4 | 29.3% | 24.4% |
| SimpleQA Verified | 38.1% | 34.7% |
| OTIS Mock AIME | 86.4% | 94.4% |
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 GLM 5.2 if…
- Higher GPQA Diamond (91.9% vs 91.0%)
- Higher FrontierMath T1–3 (59.2% vs 57.5%)
- Higher FrontierMath T4 (29.3% vs 24.4%)
- Higher SimpleQA Verified (38.1% vs 34.7%)
Choose DeepSeek V4 Flash 0731 if…
- Costs less per token — $0.113 vs $0.387 blended
- Higher OTIS Mock AIME (94.4% vs 86.4%)
- Newer model (released Jul 2026)
FAQ
Which is better, GLM 5.2 or DeepSeek V4 Flash 0731?
Across the 5 benchmarks both models have independently-run scores for, GLM 5.2 leads on 4 and DeepSeek V4 Flash 0731 leads on 1. Benchmarks are one input — price and context window are on this page too.
Is GLM 5.2 cheaper than DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 is cheaper: $0.113 versus $0.387 per million tokens blended at 3:1 input:output. Input alone: $0.252 vs $0.090. Output alone: $0.792 vs $0.180.
What context windows do GLM 5.2 and DeepSeek V4 Flash 0731 have?
GLM 5.2: 1,048,576 tokens. DeepSeek V4 Flash 0731: 1,048,576 tokens.
Who makes GLM 5.2 and DeepSeek V4 Flash 0731?
GLM 5.2 is made by Zhipu AI. DeepSeek V4 Flash 0731 is made by DeepSeek.