Back

Baidu

ERNIE 5.0 Thinking Preview

ReasoningClosed weights
Intelligence
14.3
Rank 320 of 744 measured models
Context window
128K
Rank 773 of 1199 measured models

ERNIE 5.0 Thinking Preview scores 14.3 on the Artificial Analysis Intelligence Index, ranking 320th of 744 measured models. The closest models on this index are K-EXAONE (14.4), Gemma 4 12B (14.2), and Mistral Medium 3.5 (14.2).

Artificial Analysis Indices
Intelligence14.3
Rank 320 of 744 measured models
Math85.0
Rank 46 of 270 measured models
Standard Benchmarks
MMLU Pro83.0%
Rank 60 of 349 measured models
GPQA Diamond77.7%
Rank 231 of 619 measured models
HLE13.3%
Rank 278 of 664 measured models
LiveCodeBench81.2%
Rank 24 of 343 measured models
AIME 202585.0%
Rank 46 of 270 measured models
IFBench41.4%
Rank 263 of 450 measured models
TerminalBench Hard25.0%
Rank 145 of 432 measured models
τ²-Bench83.9%
Rank 113 of 440 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy