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)
$0.31/1M
Output Price (Auto)
$0.31/1M
Cache Read (Auto)
$0.031/1M
Capabilities
Performance metrics and benchmarks
Sourced from LMArena.
Arena Score
1502.2
Overall Rank
#1 / 360
Votes
34,186
Confidence Interval
1497.9 - 1506.4
Coding
#2 / 355
8,335 votes
1551.4
Math
#3 / 349
1,981 votes
1514.5
Longer Query
#1 / 338
11,853 votes
1525.5
Creative Writing
#1 / 358
5,508 votes
1497.2
Instruction Following
#1 / 360
10,045 votes
1515.2
Hard Prompts
#1 / 360
20,448 votes
1533.2
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Chinese
#1 / 330
1,827 votes
1550.5
English
#1 / 360
15,739 votes
1515.6
Exclude Ties
#1 / 360
25,591 votes
1523.0
Expert
#1 / 309
2,574 votes
1546.0
German
#1 / 270
518 votes
1519.4
Hard Prompts English
#1 / 359
9,816 votes
1541.9
Industry Entertainment And Sports And Media
#1 / 358
6,710 votes
1491.2
Industry Legal And Government
#1 / 333
2,627 votes
1512.8
Industry Mathematical
#1 / 342
1,703 votes
1526.5
Industry Writing And Literature And Language
#1 / 359
8,071 votes
1497.0
Spanish
#1 / 248
1,148 votes
1500.0
Industry Business And Management And Financial Operations
#2 / 353
6,618 votes
1500.6
Industry Life And Physical And Social Science
#2 / 358
5,556 votes
1521.5
Industry Software And It Services
#2 / 360
12,520 votes
1539.9
Russian
#2 / 323
3,704 votes
1504.5
Multi Turn
#4 / 358
5,772 votes
1511.4
Industry Medicine And Healthcare
#5 / 329
2,451 votes
1513.8
Japanese
#6 / 228
274 votes
1490.2
French
#12 / 245
936 votes
1506.0
Korean
#21 / 240
561 votes
1430.7
Published 2026-05-27 · Matched as claude-opus-4-6-thinking
LMArena Dataset