Model Comparator

Compare up to four models using the same criteria.

Hermes 4 - Llama-3.1 405B (Reasoning)
Nous Research
ERNIE 4.5 300B A47B
Baidu

Differences only

✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.

Model Comparator
Metrics	Hermes 4 - Llama-3.1 405B (Reasoning) Nous Research	ERNIE 4.5 300B A47B Baidu
Intelligence	7.5	7.5
Math	Best: 69.7	41.3
Speed	39.6 t/s	—
TTFT	2.41 s	—
Input · $ / 1M tokens	$1×3.6 relative to the lowest price among the compared models	Best: $0.28
Output · $ / 1M tokens	$3×2.7 relative to the lowest price among the compared models	Best: $1.10
Context window	128K	Best: 131K
Reasoning	Yes	No
Open weights	Yes	Yes

Intelligence

Hermes 4 - Llama-3.1 405B (Reasoning): 7.5
ERNIE 4.5 300B A47B: 7.5

Math

Hermes 4 - Llama-3.1 405B (Reasoning): Best: 69.7
ERNIE 4.5 300B A47B: 41.3

Speed

Hermes 4 - Llama-3.1 405B (Reasoning): 39.6 t/s
ERNIE 4.5 300B A47B: —

TTFT

Hermes 4 - Llama-3.1 405B (Reasoning): 2.41 s
ERNIE 4.5 300B A47B: —

Input · $ / 1M tokens

Hermes 4 - Llama-3.1 405B (Reasoning): $1×3.6 relative to the lowest price among the compared models
ERNIE 4.5 300B A47B: Best: $0.28

Output · $ / 1M tokens

Hermes 4 - Llama-3.1 405B (Reasoning): $3×2.7 relative to the lowest price among the compared models
ERNIE 4.5 300B A47B: Best: $1.10

Context window

Hermes 4 - Llama-3.1 405B (Reasoning): 128K
ERNIE 4.5 300B A47B: Best: 131K

Reasoning

Hermes 4 - Llama-3.1 405B (Reasoning): Yes
ERNIE 4.5 300B A47B: No

Open weights

Hermes 4 - Llama-3.1 405B (Reasoning): Yes
ERNIE 4.5 300B A47B: Yes

Each reasoning level remains a separate configuration.

Score and cost

Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.

Hermes 4 - Llama-3.1 405B (Reasoning)7.5 · $1.50
ERNIE 4.5 300B A47B7.5 · $0.485