Open flagship GLM for long-horizon coding agents and million-token context work
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Agentic Index | agentic | 43.1 | — | mirror | openrouter | Jul 23, 2026 |
| AA Coding Index | coding | 68.8 | — | mirror | openrouter | Jul 23, 2026 |
| AA Intelligence Index | intelligence | 51.1 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — 3d | preference | 1358 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — agenticgamedev | preference | 1193 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — androidnative | preference | 1234 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — asciiart | preference | 1234 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — codecategories | preference | 1341 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — dataviz | preference | 1300 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — fullstack | preference | 1288 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — gamedev | preference | 1350 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — godotgamedev | preference | 1142 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — htmlslides | preference | 1204 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — mobileapps | preference | 1238 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — python-pptxslides | preference | 1188 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — svg | preference | 1259 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — uicomponent | preference | 1333 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — webapps | preference | 1274 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — website | preference | 1338 | — | mirror | openrouter | Jul 23, 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 |
|---|---|---|---|---|---|---|
| AkashML | fp8 | 97K | $0.77 · $2.42 | 95.35% | — | — |
| Alibaba | — | 1.0M | $0.826 · $2.6 | 99.82% | — | — |
| Alibaba | — | 1.0M | $2.31 · $7.26 | 99.52% | — | — |
| Ambient | fp8 | 101K | $1.05 · $4.4 | 97.46% | — | — |
| AtlasCloud | fp8 | 1.0M | $1.26 · $3.96 | 99.59% | — | — |
| Baidu | fp8 | 1.0M | $1.26 · $3.96 | 99.75% | — | — |
| BaseTen | fp8 | 524K | $2.1 · $6.6 | 99.95% | — | — |
| BaseTen | fp8 | 524K | $1.4 · $4.4 | 99.95% | — | — |
| Chutes | fp4 | 1.0M | $1.4 · $4.4 | 94.53% | — | — |
| Cloudflare | — | 262K | $1.4 · $4.4 | 99.99% | — | — |
| CoreWeave | fp4 | 262K | $1.39 · $4.4 | 99.86% | — | — |
| Decart | fp8 | 1.0M | $1.2 · $2.5 | 98.52% | — | — |
| DeepInfra | fp4 | 1.0M | $0.93 · $3 | 98.38% | — | — |
| DigitalOcean | — | 262K | $1.05 · $4.4 | 94.44% | — | — |
| Fireworks | — | 1.0M | $1.4 · $4.4 | 99.66% | — | — |
| Fireworks | — | 1.0M | $2.1 · $6.6 | 99.30% | — | — |
| Friendli | — | 1.0M | $1.4 · $4.4 | 98.78% | — | — |
| GMICloud | fp8 | 1.0M | $0.924 · $2.9 | 98.58% | — | — |
| Inceptron | fp4 | 1.0M | $0.94 · $2.9 | 95.33% | — | — |
| Io Net | fp8 | 262K | $3.09 · $6.75 | 98.92% | — | — |
| Ionstream | fp4 | 1.0M | $1.4 · $4.4 | 94.70% | — | — |
| Morph | — | 1.0M | $1.1 · $4.1 | 95.28% | — | — |
| Novita | fp8 | 1.0M | $0.767 · $2.41 | 97.67% | — | — |
| Parasail | fp4 | 262K | $1.4 · $4.4 | 98.95% | — | — |
| Phala | — | 1.0M | $1.4 · $4.4 | 98.31% | — | — |
| Sail Research | fp8 | 1.0M | $1.12 · $3.52 | 42.72% | — | — |
| SiliconFlow | fp8 | 1.0M | $1.3 · $4.09 | 99.61% | — | — |
| StreamLake | fp8 | 1.0M | $0.768 · $2.41 | 98.97% | — | — |
| Together | — | 262K | $1.4 · $4.4 | 99.52% | — | — |
| Venice | fp8 | 1M | $1.4 · $4.4 | 99.04% | — | — |
| Wafer | fp4 | 1.0M | $3 · $10.25 | 99.85% | — | — |
| Wafer | fp4 | 1.0M | $1.2 · $4.1 | 99.75% | — | — |
| Z.AI | fp8 | 1.0M | $1.4 · $4.4 | 99.57% | — | — |