Native multimodal GLM model for efficient coding and long-horizon agent tasks
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Agentic Index | agentic | 50.9 | — | mirror | openrouter | Sep 20, 2026 |
| 50.9 | — | independent | aa | Sep 20, 2026 | ||
| AA Coding Index | coding | 71.5 | — | mirror | openrouter | Aug 27, 2026 |
| 71.5 | — | independent | aa | Aug 27, 2026 | ||
| AA Intelligence Index | intelligence | 41.8 | — | mirror | openrouter | Sep 20, 2026 |
| 41.8 | — | independent | aa | Sep 20, 2026 | ||
| Design Arena — 3d | preference | 1353 | — | mirror | openrouter | Sep 19, 2026 |
| Design Arena — asciiart | preference | 1288 | — | mirror | openrouter | Sep 21, 2026 |
| Design Arena — codecategories | preference | 1296 | — | mirror | openrouter | Sep 21, 2026 |
| Design Arena — dataviz | preference | 1277 | — | mirror | openrouter | Sep 21, 2026 |
| Design Arena — gamedev | preference | 1310 | — | mirror | openrouter | Sep 20, 2026 |
| Design Arena — svg | preference | 1312 | — | mirror | openrouter | Sep 21, 2026 |
| Design Arena — uicomponent | preference | 1334 | — | mirror | openrouter | Sep 21, 2026 |
| Design Arena — website | preference | 1284 | — | mirror | openrouter | Sep 19, 2026 |
| LMArena Text | preference | 1472 | — | crowd | lmarena | Sep 13, 2026 |
| LMArena Vision | preference | 1299 | — | crowd | lmarena | Sep 13, 2026 |
| LMArena WebDev | preference | 1607 | — | crowd | lmarena | Sep 11, 2026 |
| Median output speed | speed | 95 tok/s | — | independent | aa | Sep 21, 2026 |
| Median time to first token | speed | 2.52s | — | independent | aa | Sep 20, 2026 |
Includes index data from Artificial Analysis.
Providers
Live operational stats per hosting endpoint, via OpenRouter.
| Provider | Quant | Context | $/1M in · out | Uptime 24h | Latency | Throughput |
|---|---|---|---|---|---|---|
| AtlasCloud | fp8 | 1.0M | $0.15 · $0.5 | 98.65% | — | — |
| BaseTen | fp8 | 1.0M | $0.15 · $0.5 | 99.67% | — | — |
| Cloudflare | — | 1.3M | $0.15 · $0.5 | 99.67% | — | — |
| CoreWeave | nvfp4 | 1.0M | $0.15 · $0.5 | 99.78% | — | — |
| Crusoe | fp4 | 1.0M | $0.15 · $0.5 | 94.95% | — | — |
| DeepInfra | fp4 | 1.0M | $0.075 · $0.25 | 99.17% | — | — |
| DigitalOcean | — | 1.0M | $0.15 · $0.5 | 97.67% | — | — |
| Fireworks | — | 1.0M | $0.15 · $0.5 | 99.07% | — | — |
| Friendli | — | 1.0M | $0.15 · $0.5 | 99.27% | — | — |
| GMICloud | fp8 | 1.0M | $0.075 · $0.25 | 99.05% | — | — |
| InferenceNet | fp4 | 1.0M | $0.09 · $0.28 | 96.44% | — | — |
| Io Net | fp8 | 262K | $0.15 · $0.5 | 99.40% | — | — |
| Modal | fp8 | 1.0M | $0.45 · $1.5 | 99.93% | — | — |
| Morph | — | 1.0M | $0.1 · $0.35 | 99.96% | — | — |
| Near AI | fp8 | 1.0M | $0.15 · $0.5 | 98.83% | — | — |
| NextBit | fp8 | 1.0M | $0.18 · $0.6 | 98.30% | — | — |
| Novita | fp8 | 1.0M | $0.132 · $0.44 | 99.37% | — | — |
| Parasail | fp8 | 1.0M | $0.15 · $0.5 | 99.26% | — | — |
| Phala | fp8 | 1.0M | $0.15 · $0.5 | 98.07% | — | — |
| Reka | fp8 | 262K | $0.15 · $0.5 | 99.52% | — | — |
| Relace | — | 1.0M | $0.09 · $0.3 | 99.93% | — | — |
| Sail Research | fp8 | 1.0M | $0.143 · $0.475 | 98.24% | — | — |
| Sail Research | fp8 | 1.0M | $0.143 · $0.475 | 98.11% | — | — |
| SiliconFlow | fp8 | 1.0M | $0.15 · $0.5 | 99.67% | — | — |
| StreamLake | fp8 | 1.0M | $0.141 · $0.47 | 99.34% | — | — |
| Together | — | 1.0M | $0.15 · $0.5 | 99.12% | — | — |
| Venice | — | 1.0M | $0.15 · $0.5 | 99.15% | — | — |
| Wafer | — | 1.0M | $0.1 · $0.35 | 99.76% | — | — |
| Z.AI | fp8 | 1.0M | $0.15 · $0.5 | 99.78% | — | — |