whatmodel.sh / ERNIE 5.0 Preview (1220)

ERNIE 5.0 Preview (1220)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

ERNIE 5.0 Preview (1220) is a closed-weights language model from Baidu, released January 2026.

Catalogue identity notes

Comparison-only. Arena entry 'ernie-5.0-preview-1220' (vision). Released 2026-01: month Baidu publicly named ERNIE-5.0-Preview-1220 (Vision Arena). Dated ERNIE 5.0 preview snapshot evaluated on Vision Arena and publicly named by Baidu; no Qianfan id.

67.2±3.9comparison only: no current run option verifiedfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of ERNIE 5.0 Preview (1220), out of 1132 with a score, then more from Baidu.

#modelscorewhereRAMreleased
143Claude Opus 4 Anthropic67±1comparison only2025-05
144ERNIE 5.0 Preview (1022) Baidu67±3comparison only2025-11
145ERNIE 5.0 Preview (1220) Baidu67±4comparison only2026-01
146K-EXAONE 2.0 (750B-A37B) LG AI Research67±1local~791GB2026-07
147Claude Opus 4.1 Anthropic67±1comparison only2025-08
more from Baidu
68ERNIE 5.1 Baidu73±3comparison only2026-05
93ERNIE 5.0 Preview (1203) Baidu71±3comparison only2025-12
129ERNIE 5.0 (0110) Baidu68±3comparison only2026-01

see all LLMs · find the ones that fit your machine

$ what it's good at

vision & documents▁▁▃▃▂▃▅▅▇▇█▃ #76 of 199 * · 93% of its score · 1 test

Beats DeepSeek V4 Flash Vision (Exp), GPT-5, Inkling Small (266B-A12B) here, though they rank higher overall. Trails Gemma 4 26B-A4B, Claude Haiku 4.5, Qwen3.6 Flash here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena vision (style controlled)1218.9 ✎▁▁▂▂▂▂▄▅▅▆██ beats 84/145avg 1068▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 93%blunt

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · LMArena leaderboard dataset 93%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
LMArena leaderboard dataset1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 93%CC BY 4.0
prior · pull toward the middle▇▇ 7%
weighted average= 67.2

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json