Private AI
Extended context model supporting up to 1M tokens
Context Window
1.0M
Max Output
4.1K
Input Price (Auto)
$0.18/1M
Output Price (Auto)
$0.18/1M
Cache Read (Auto)
$0.088/1M
Performance metrics and benchmarks
Sourced from LMArena.
Arena Score
1273.1
Overall Rank
#276 / 383
Votes
9,788
Confidence Interval
1266.2 - 1280.1
Coding
#269 / 378
1,718 votes
1308.6
Math
#267 / 370
1,191 votes
1246.3
Longer Query
#278 / 361
1,174 votes
1267.6
Creative Writing
#272 / 381
1,547 votes
1241.0
Instruction Following
#274 / 383
3,766 votes
1255.7
Hard Prompts
#275 / 383
2,970 votes
1277.7
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
German
#239 / 287
371 votes
1227.3
Korean
#241 / 259
302 votes
1103.9
Chinese
#242 / 355
1,227 votes
1302.9
Industry Legal And Government
#253 / 356
556 votes
1311.7
Industry Mathematical
#261 / 365
1,067 votes
1264.2
Industry Medicine And Healthcare
#266 / 353
554 votes
1280.2
Expert
#268 / 332
514 votes
1250.4
Russian
#269 / 346
1,264 votes
1260.3
Multi Turn
#272 / 381
1,631 votes
1258.4
Exclude Ties
#273 / 383
6,229 votes
1191.4
Hard Prompts English
#274 / 382
1,775 votes
1285.1
Industry Life And Physical And Social Science
#274 / 381
1,590 votes
1290.2
Industry Software And It Services
#274 / 383
2,832 votes
1296.4
English
#275 / 383
5,169 votes
1287.9
Non English
#275 / 383
4,619 votes
1247.6
Industry Entertainment And Sports And Media
#277 / 381
1,605 votes
1233.8
Industry Writing And Literature And Language
#278 / 382
2,609 votes
1253.8
Industry Business And Management And Financial Operations
#283 / 376
1,186 votes
1245.1
Published 2026-08-03 · Matched as glm-4-0520
LMArena Dataset