Back

Baidu

ERNIE 4.5 300B A47B

Open weightsHugging Face
Intelligence
7.5
Rank 533 of 744 measured models
Price/1M
$0.485
Rank 274 of 659 measured models
Context window
131K
Rank 738 of 1199 measured models

ERNIE 4.5 300B A47B scores 7.5 on the Artificial Analysis Intelligence Index, ranking 533rd of 744 measured models. The closest models on this index are Devstral Small 2 (7.5), Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) (7.5), and Nous: Hermes 4 405B (7.5). At $0.485 per million tokens (3:1 input/output blended price), it is cheaper than Nous: Hermes 4 405B ($1.50).

Artificial Analysis Indices
Intelligence7.5
Rank 533 of 744 measured models
Math41.3
Rank 153 of 270 measured models
Standard Benchmarks
MMLU Pro77.6%
Rank 149 of 349 measured models
GPQA Diamond81.1%
Rank 195 of 619 measured models
HLE3.3%
Rank 639 of 664 measured models
LiveCodeBench46.7%
Rank 161 of 343 measured models
MATH-50093.1%
Rank 57 of 202 measured models
AIME 202449.3%
Rank 60 of 194 measured models
AIME 202541.3%
Rank 153 of 270 measured models
IFBench39.1%
Rank 287 of 450 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