Private AI
Z.ai's native multimodal agent model for vision-based coding and agent workflows. This is the standard non-thinking variant for image, video, and text inputs, tuned for perceive-plan-execute loops, complex coding, and tool-driven task execution. Not included in the subscription.
Added Apr 1, 2026
Context Window
202.8K
Max Output
131.1K
Input Price (Auto)
$1.20/1M
Output Price (Auto)
$4.00/1M
Cache Read (Auto)
$0.24/1M
Capabilities
Performance metrics and benchmarks
Sourced from LMArena.
Arena Score
1440.1
Overall Rank
#66 / 374
Votes
3,358
Confidence Interval
1429.8 - 1450.4
Coding
#46 / 369
956 votes
1502.8
Longer Query
#63 / 352
1,457 votes
1449.7
Creative Writing
#97 / 372
554 votes
1390.8
Instruction Following
#74 / 374
1,112 votes
1425.2
Hard Prompts
#68 / 374
2,155 votes
1459.3
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
English
#56 / 374
1,484 votes
1459.4
Expert
#57 / 322
314 votes
1473.1
Industry Software And It Services
#58 / 374
1,306 votes
1485.3
Hard Prompts English
#59 / 373
982 votes
1470.1
Exclude Ties
#67 / 374
2,477 votes
1436.0
Industry Life And Physical And Social Science
#69 / 372
486 votes
1454.3
Industry Writing And Literature And Language
#70 / 373
810 votes
1416.5
Non English
#76 / 374
1,867 votes
1420.2
Multi Turn
#78 / 372
553 votes
1437.4
Industry Business And Management And Financial Operations
#80 / 367
697 votes
1428.4
Russian
#82 / 336
317 votes
1421.9
Industry Entertainment And Sports And Media
#87 / 372
746 votes
1395.8
Industry Legal And Government
#97 / 346
247 votes
1427.3
Industry Medicine And Healthcare
#130 / 343
199 votes
1419.0
Published 2026-07-10 · Matched as glm-5v-turbo
LMArena Dataset