GLM-5.2 Low
| Released | 2026-06-13 |
|---|---|
| Price per 1M | $1.20 in · $4.18 out |
| Overall score | 54.9 (early, few results) |
| Context window | 1,000,000 tokens |
| Provider | Zhipu AI |
| Weights | Open weights |
| Configuration | Low |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 54.9 | 5 | |
| Overall: Coding | 54.3 | 3 | |
| Overall: Reasoning | 54.9 | 5 | |
| Overall: Agentic work | 54.3 | 3 | |
| Reasoning | 54.3 | 3 | |
| Math | 55.8 | 2 | |
| Value vs price | +2.8 |
Evidence
Reasoning 54.3 ±6.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 87.9% | Epoch AI | 2026-08-10 |
| Chess Puzzles | 18.0% | Epoch AI | 2026-10-14 |
| Mystery Game Puzzles | 19.0% | Epoch AI | 2026-08-27 |
Math 55.8 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 54.7% | Epoch AI | 2026-08-29 |
| OTIS Mock AIME 2024-2025 | 75.6% | Epoch AI | 2026-08-10 |
Names matched to this model
glm-5-2-low