Private AI
ArliAI-hosted Gemma 4 31B reasoning-distilled finetune for structured scene planning, dialogue, and multimodal chat.
Added May 1, 2026
Context Window
262.1K
Max Output
N/A
Avg output tokens (7d)
564 tokens
Input Price (Auto)
$0.27/1M
Output Price (Auto)
$0.27/1M
Cache Read (Auto)
$0.027/1M
Capabilities
Performance metrics and benchmarks
Sourced from LMArena.
Arena Score
1505.4
Overall Rank
#2 / 383
Votes
67,203
Confidence Interval
1501.8 - 1509.0
Coding
#3 / 378
17,433 votes
1551.1
Math
#5 / 370
3,466 votes
1518.1
Longer Query
#1 / 361
27,108 votes
1524.4
Creative Writing
#2 / 381
11,623 votes
1500.0
Instruction Following
#2 / 383
21,019 votes
1513.6
Hard Prompts
#2 / 383
42,246 votes
1533.7
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
English
#1 / 383
30,841 votes
1515.9
Hard Prompts English
#1 / 382
20,073 votes
1537.9
Multi Turn
#1 / 381
11,497 votes
1518.0
Exclude Ties
#2 / 383
51,279 votes
1525.2
German
#2 / 287
1,078 votes
1512.7
Industry Entertainment And Sports And Media
#2 / 381
14,504 votes
1494.4
Industry Life And Physical And Social Science
#2 / 381
10,927 votes
1528.9
Industry Mathematical
#2 / 365
3,307 votes
1527.9
Industry Writing And Literature And Language
#2 / 382
16,771 votes
1500.2
Expert
#3 / 332
5,661 votes
1545.7
Industry Legal And Government
#3 / 356
5,433 votes
1511.3
Industry Medicine And Healthcare
#3 / 353
4,960 votes
1520.4
Industry Software And It Services
#3 / 383
25,510 votes
1540.1
Polish
#3 / 211
1,322 votes
1498.7
Russian
#3 / 346
6,992 votes
1507.2
Industry Business And Management And Financial Operations
#4 / 376
13,339 votes
1501.9
Non English
#4 / 383
36,360 votes
1489.9
Chinese
#5 / 355
3,810 votes
1555.3
Spanish
#5 / 269
2,190 votes
1495.1
French
#7 / 267
2,183 votes
1510.3
Japanese
#8 / 245
657 votes
1490.6
Korean
#15 / 259
1,114 votes
1446.1
Published 2026-08-03 · Matched as claude-opus-4-6-thinking
LMArena Dataset