Budget GLM lane for fast coding help, routing, and everyday automation
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Intelligence Index | intelligence | 22.9 | — | independent | aa | Jul 24, 2026 |
| Design Arena — 3d | preference | 1180 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — codecategories | preference | 1210 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — dataviz | preference | 1157 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — gamedev | preference | 1193 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — svg | preference | 1087 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — uicomponent | preference | 1248 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — website | preference | 1221 | — | mirror | openrouter | Jul 23, 2026 |
| Median output speed | speed | 104 tok/s | — | independent | aa | Jul 24, 2026 |
| Median time to first token | speed | 1.17s | — | independent | aa | Jul 24, 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 |
|---|---|---|---|---|---|---|
| Cloudflare | — | 131K | $0.061 · $0.4 | 98.81% | — | — |
| DeepInfra | bf16 | 203K | $0.06 · $0.4 | 98.40% | — | — |
| Novita | bf16 | 200K | $0.07 · $0.4 | 87.90% | — | — |
| Venice | fp8 | 128K | $0.125 · $0.5 | 94.38% | — | — |