GLM-5 Thinking
| Released | 2026-02-12 |
|---|---|
| Price per 1M | $0.60 in · $2.69 out |
| Overall score | 52.8 · rank 230 |
| Context window | 204,800 tokens |
| Provider | Zhipu AI |
| Weights | Open weights |
| Configuration | Thinking |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 52.8 | 230 | 6 |
| Overall: Coding | 52.2 | 231 | 5 |
| Overall: Reasoning | 53.6 | 214 | 3 |
| Overall: Agentic work | 53.6 | 224 | 4 |
| Overall: Frontend | 48.7 | 232 | 3 |
| Coding | 53.4 | 207 | 2 |
| Reasoning | 53.9 | 214 | 2 |
| Knowledge | 52.8 | 101 | 1 |
| Frontend | 46.4 | 138 | 1 |
| Value vs price | +2.3 | 181 |
Evidence
Coding 53.4 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SWE-bench Verified (Vals run) | 71.4% | Vals AI | 2026-09-01 |
| LiveCodeBench (Vals run) | 81.9% | Vals AI | 2026-09-01 |
Reasoning 53.9 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond (Vals run) | 83.3% | Vals AI | 2026-09-01 |
| Kagi Reasoning Benchmark | 75.0% | Kagi | 2026-11-11 |
Knowledge 52.8 ±4.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 86.0% | Vals AI | 2026-09-01 |
Frontend 46.4 ±0.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 23.4% | Vals AI | 2026-11-09 |
Names matched to this model
glm-5-thinking