ERNIE 5.1 is the latest Wenxin model, with broad upgrades to agentic workflows, knowledge, reasoning, and deep search. ⚠️ Note: privacy and logging guarantees may be limited.
Added May 10, 2026
Context Window
119.0K
Max Output
64.0K
Avg output tokens (7d)
291 tokens
Input Price (Auto)
$0.75/1M
Output Price (Auto)
$3.00/1M
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from LMArena.
Arena Score
1468.1
Overall Rank
#39 / 395
Votes
37,102
Confidence Interval
1463.5 - 1472.8
Category Scores
Coding
#35 / 390
10,304 votes
1514.0
Math
#30 / 379
1,891 votes
1476.1
Longer Query
#57 / 373
15,393 votes
1465.9
Creative Writing
#63 / 393
5,907 votes
1428.3
Instruction Following
#49 / 395
11,739 votes
1453.2
Hard Prompts
#42 / 395
24,032 votes
1487.7
Additional Categories22
Industry Medicine And Healthcare
#21 / 363
2,677 votes
1493.4
Industry Business And Management And Financial Operations
#22 / 388
7,421 votes
1476.8
Industry Mathematical
#25 / 374
1,911 votes
1488.1
Industry Software And It Services
#26 / 395
14,746 votes
1508.7
English
#29 / 395
17,027 votes
1478.9
German
#34 / 296
725 votes
1470.5
Industry Life And Physical And Social Science
#34 / 393
5,926 votes
1487.6
Hard Prompts English
#35 / 393
11,723 votes
1492.8
Spanish
#38 / 277
1,264 votes
1461.3
Exclude Ties
#39 / 395
28,177 votes
1474.0
Expert
#40 / 345
3,418 votes
1493.6
Korean
#41 / 265
638 votes
1422.0
French
#42 / 276
1,464 votes
1483.7
Japanese
#42 / 261
494 votes
1437.7
Non English
#43 / 395
20,075 votes
1453.6
Polish
#44 / 219
762 votes
1463.2
Multi Turn
#46 / 393
6,417 votes
1472.5
Russian
#47 / 359
3,884 votes
1463.9
Chinese
#49 / 367
1,751 votes
1498.6
Industry Legal And Government
#56 / 368
2,931 votes
1464.3
Industry Writing And Literature And Language
#59 / 394
8,945 votes
1441.9
Industry Entertainment And Sports And Media
#61 / 393
7,812 votes
1428.6
Published 2026-08-27 · Matched as ernie-5.1
LMArena DatasetProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare ERNIE 5.1 with similar models from the same provider or model family.
ERNIE 5.1 Thinking
ernie-5.1:thinkingERNIE 5.1 Thinking is the latest Wenxin model with explicit reasoning enabled for harder planning, coding, math, and agentic tasks. ⚠️ Note: privacy and logging guarantees may be limited.
Ernie 5.0 Thinking Preview
ernie-5.0-thinking-previewERNIE 5.0 Thinking is Baidu's next-generation step-by-step reasoning model, providing stronger logical thinking, code generation, and tool-use capabilities with explicit thinking traces. ⚠️ Note: This model routes through Baidu, a Chinese entity - privacy and logging guarantees may be limited.
ERNIE X1.1
ernie-x1.1-previewThe Wenxin large model X1.1 has made significant improvements in question answering, tool invocation, intelligent agents, instruction following, logical reasoning, mathematics, and coding tasks, with notable enhancements in factual accuracy. The context length has been extended to 64K tokens, supporting longer inputs and dialogue history, which improves the coherence of long-chain reasoning while maintaining response speed. ⚠️ Note: This model routes through Baidu (China) — privacy and logging guarantees may be limited.
Chimera X
google/gemma-4-26b-a4b-it-chimeraxChimera X is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.
Dark Soul
google/gemma-4-26b-a4b-it-darksoulDark Soul is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.
Luminous Mirror
google/gemma-4-26b-a4b-it-luminousLuminous Mirror is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.
