Quality
Highest overall scores
- 1
Z.ai: GLM 5.251.1 - 2Z.ai: GLM 5.140.2
- 3Z.ai: GLM 4.7 Flash0
Z.ai model benchmarks.
Compare Z.ai models across answer quality, coding, complex tasks, speed, price, and context size.
Response speed
Fastest output in this sample
- 1Z.ai: GLM 5.2159 t/s
- 2Z.ai: GLM 5.1146 t/s
- 3Z.ai: GLM 4.7 Flash19 t/s
Input price
Lowest price per 1M tokens
- 1Z.ai: GLM 4.7 Flash$0.06/1M
- 2Z.ai: GLM 5.2$0.77/1M
- 3Z.ai: GLM 5.1$0.97/1M
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better
Quality benchmarks
Compare Z.ai model capability.
Performance and price
Compare practical tradeoffs.
All Z.ai models.
3 models in the current catalogue.
| Model | Links | |||||
|---|---|---|---|---|---|---|
| Z.ai: GLM 5.2 | 51.1 | 159 t/s | 1M | $0.77 | $2.42 | |
| Z.ai: GLM 5.1 | 40.2 | 146 t/s | 204.8K | $0.97 | $3.04 | |
| Z.ai: GLM 4.7 Flash | 0 | 19 t/s | 202.8K | $0.06 | $0.40 |
Z.ai technical benchmarks.
Compare named evaluation records available for Z.ai models. Missing results remain blank rather than being estimated.
| Benchmark | Area | GLM 5.2 | GLM 5.1 | GLM 4.7 Flash | Source |
|---|---|---|---|---|---|
| Intelligence Index | overallQuality | 51.1 | 40.2 | — | OpenRouter / artificial-analysis |
| Coding Index | coding | 68.8 | 55.8 | — | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 43.1 | 29.9 | — | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | 89.5 | 86.8 | 75.2 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 40.1 | 28 | 14.4 | OpenRouter model benchmarks |
| IFBench | IFBench | 73.3 | 76.3 | — | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | 99.1 | 97.7 | — | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 71.3 | 62.3 | — | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | 50.5 | 37.8 | — | OpenRouter model benchmarks |
| CritPt | CritPt | 20.9 | 4.6 | — | OpenRouter model benchmarks |
| SciCode | SciCode | 50.5 | 43.8 | — | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | 50.8 | 43.2 | — | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 25.1 | 24.2 | — | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 71.9 | 70.6 | — | OpenRouter model benchmarks |
| SWE-bench Verified | Coding | — | — | 59.2 | OpenEvals/leaderboard-data |