GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...
text+image+video->text| Provider | Region / Tag | Context | Input/M | Output/M | Uptime 1d | Latency | Quant | Cache |
|---|---|---|---|---|---|---|---|---|
| Novita | novita/bf16 | 131K | $0.300 | $0.900 | 98.90% | - | bf16 | - |
| Z.AI | z-ai/fp8 | 131K | $0.300 | $0.900 | 91.10% | - | fp8 | ✓ |
| Rank | Category | Variant | Trend | Elo | Votes |
|---|---|---|---|---|---|
| #129 | Industry Legal And Government | - | 1401 | 202 | |
| #138 | Industry Life And Physical And Social Science | - | 1404 | 466 | |
| #140 | Industry Entertainment And Sports And Media | - | 1349 | 510 | |
| #145 | English | - | 1394 | 1,288 | |
| #147 | Creative Writing | - | 1343 | 417 | |
| #147 | Instruction Following | - | 1368 | 731 | |
| #148 | Exclude Ties | - | 1351 | 2,005 | |
| #148 | Hard Prompts English | - | 1404 | 714 | |
| #148 | Non English | - | 1359 | 1,514 | |
| #148 | Overall | - | 1377 | 2,802 | |
| #149 | Longer Query | - | 1379 | 660 | |
| #150 | Industry Writing And Literature And Language | - | 1355 | 607 | |
| #152 | Coding | - | 1418 | 534 | |
| #152 | Industry Software And It Services | - | 1408 | 924 | |
| #155 | Multi Turn | - | 1367 | 480 | |
| #156 | Industry Business And Management And Financial Operations | - | 1368 | 539 | |
| #158 | Hard Prompts | - | 1383 | 1,492 | |
| #168 | Russian | - | 1347 | 285 |
| Rank | Category | Variant | Trend | Elo | Votes |
|---|---|---|---|---|---|
| #69 | Creative Writing | - | 1134 | 195 | |
| #69 | Creative Writing Vision | - | 1142 | 195 | |
| #73 | Diagram | - | 1185 | 549 | |
| #74 | English | - | 1175 | 960 | |
| #74 | Ocr | - | 1170 | 1,431 | |
| #76 | Overall | - | 1164 | 2,332 | |
| #82 | Homework | - | 1153 | 283 |